Publications | Deep Learning ONR MURI

Patil, P., Du, J.-H., and Tibshirani, R.J. Optimal ridge regularization for out-of-distribution prediction. International Conference on Machine Learning, 2024.
Saragadam, V., Han, Z., Boominathan, V., Huang, L., Tan, S., Fröch, J. E., Böhringer, K. F., Baraniuk, R. G., Majumdar, A., and Veeraraghavan, A. Foveated Thermal Computational Imaging in the Wild Using All-Silicon Meta-Optics. Optica, 2024.
LeJeune, D., Patil, P., Javadi, H., Baraniuk, R. G., and Tibshirani, R. J. Asymptotics of the Sketched Pseudoinverse. SIAM Journal on Mathematics of Data Science (SIMODS), 2024.
Saragadam, V., Balestriero, R., Veeraraghavan, A., and Baraniuk, R. G. DeepTensor: Low-Rank Tensor Decomposition with Deep Network Priors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024.
Kota, P. K., Vu, H.-A., LeJeune, D., Han, M., Syed, S., Baraniuk, R. G., and Drezek, R. A. Expanding Multiplexing on Sensor-Constrained Microfluidic Partitioning Systems. Analytical Chemistry, 2023.
Balestriero, R., Humayun, A. I., and Baraniuk, R. G. On the Geometry of Deep Learning. Notices of the American Mathematical Society, August 2024.
Alemohammad, S., Humayun, A. I., Agarwal, S., Collomosse, J., and Baraniuk, R. G. Self-Improving Diffusion Models with Synthetic Data. Preprint, 2024.
Humayun, A. I., Balestriero, R., and Baraniuk, R. G. Deep Networks Always Grok and Here is Why. International Conference on Machine Learning (ICML), 2024.
Nguyen, T., Uribe, C. A., Nguyen, T. M., and Baraniuk, R. G. PIDformer: Transformer Meets Control Theory. International Conference on Machine Learning (ICML), 2024.
Vyas, K., Humayun, A. I., Dashpute, A., Baraniuk, R. G., Veeraraghavan, A., and Balakrishnan, G. Learning Transferable Features for Implicit Neural Representations. Neural Information Processing Systems (NeurIPS), 2024.
Ronen, O., Humayun, A. I., Balestriero, R., Baraniuk, R. G., and Yu, B. ScaLES: Scalable Latent Exploration Score for Pre-Trained Generative Networks. Preprint (International Conference on Learning Representations), 2025.
Roy, A., Shah, A., Shah, K., Roy, A., and Chellappa, R. Cap2aug: Caption guided image to image data augmentation. IEEE/CVF Winter Conference on Applications of Computer Vision (WCAV), 2025.
Roy, A., Roy, A., Mitra, S., and Ghosh, K. BRI3L: A Brightness Illusion Image Dataset for Identification and Localization of Regions of Illusory Perception. IEEE International Conference on Image Processing (ICIP), 2024.
Roy, A., Borse, S., Kadambi, S., Garrepalli, R., Das, D., Mahajan, S., Park, H., Nayak, A., Chellappa, R., Hayat, M., and Porikli, F. DuoLoRA: Cycle-consistent and Rank-disentangled content-style personalization. Preprint, 2024.
Binev, P., Bonito, A., Cohen, A., Dahmen, W., DeVore, R., and Petrova, G. Solving PDEs with incomplete information. SIAM Journal on Numerical Analysis, 2024.
Bonito, A., DeVore, R., Petrova, G., and Siegel, J. W. Convergence and error control of consistent PINNs for elliptic PDEs. Preprint, 2024.
Cohen, A., DeVore, R., and Tadmor, E. Constructions of bounded solutions of div (u) = f in critical spaces. Multiscale, Nonlinear and Adaptive Approximation, 2024.
DeVore, R., Petrova, G., and Wojtaszczyk, P. A note on best n-term approximation for generalized Wiener classes. Multiscale, Nonlinear and Adaptive Approximation, 2024.
Dezoort, G., and Hanin, B. Principles for initialization and architecture selection in graph neural networks with ReLU activations. Preprint, 2024.
Dressler, M., Foucart, S., Joldes, M., de Klerk, E., Lasserre, J. B., and Xu, Y. Optimization-aided construction of multivariate Chebyshev polynomials. Journal of Approximation Theory, 2024.
Dressler, M., Foucart, S., Joldes, M., de Klerk, E., Lasserre, J.-B., and Xu, Y. Least multivariate Chebyshev polynomials on diagonally determined domains. Preprint, 2024.
Foucart, S. Linearly embedding sparse vectors from L2 to L1 via deterministic dimension-reducing maps. Explorations in the Mathematics of Data Science, 2024.
Foucart, S., and Liao, C. S-procedure relaxation: a case of exactness involving Chebyshev centers. Explorations in the Mathematics of Data Science, 2024.
Foucart, S., and Paouris, G. Near-optimal estimation of linear functionals with log-concave observation errors. Information and Inference, 2023.
S. Foucart, C. Liao, Radius of information for two intersected centered hyperellipsoids and implications in optimal recovery from inaccurate data. Journal of Complexity, 2024
Foucart, S., and Hengartner, N. Worst-case learning under a multifidelity model. SIAM/ASA Journal on Uncertainty Quantification, 2024.
Hanin, B. Random Fully Connected Neural Networks as Perturbatively Solvable Hierarchies. Journal of Machine Learning Research, 2024.
Hanin, B., and Zlokapa, A. Bayesian Inference with Deep Weakly Nonlinear Networks. Preprint, 2024.
Klusowski, J. M., and Siegel, J. W. Sharp Convergence Rates for Matching Pursuit. Preprint, 2024.
Mao, T., Siegel, J. W., and Xu, J. Approximation Rates for Shallow ReLUk Neural Networks on Sobolev Spaces via the Radon Transform. Preprint, 2024.
Siegel, J. W. Optimal Approximation Rates for Deep ReLU Neural Networks on Sobolev and Besov Spaces. Journal of Machine Learning Research, 2023.
Siegel, J. W. Sharp lower bounds on the manifold Widths of Sobolev and Besov spaces. Journal of Complexity, 2024.
Dym, N., Lawrence, H., and Siegel, J. W. Equivariant Frames and the Impossibility of Continuous Canonicalization. International Conference on Machine Learning, 2024.
Bansal, A., Borgnia, E., Chu, H.-M., Li, J., Kazemi, H., Huang, F., Goldblum, M., Geiping, J., and Goldstein, T. Cold diffusion: Inverting arbitrary image transforms without noise. Advances in Neural Information Processing Systems (NeurIPS), 2023.
Hans, A., Schwarzschild, A., Cherepanova, V., Kazemi, H., Saha, A., Goldblum, M., Geiping, J., and Goldstein, T. Spotting llms with binoculars: Zero-shot detection of machine-generated text. Preprint, 2024.
Hans, A., Wen, Y., Jain, N., Kirchenbauer, J., Kazemi, H., Singhania, P., Singh, S., Somepalli, G., Geiping, J., Bhatele, A., and Goldstein, T. Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs. Advances in Neural Information Processing Systems (NeurIPS), 2024.
Kazemi, H., Chegini, A., Geiping, J., Feizi, S., and Goldstein, T. What do we learn from inverting CLIP models? Preprint, 2024.
Shenouda, J., Parhi, R., Lee, K., and Nowak, R. D. Variation spaces for multi-output neural networks: Insights on multi-task learning and network compression. Journal of Machine Learning Research, 2024.
Shenouda, J., Zhou, Y., and Nowak, R. D. ReLUs Are Sufficient for Learning Implicit Neural Representations. International Conference on Machine Learning (ICML), 2024.
Zuo, X., Osher, S., and Li, W. Gradient-adjusted underdamped Langevin dynamics for sampling. Preprint, 2024.
McKenzie, D., Heaton, H., Li, Q., Wu Fung, S., Osher, S., and Yin, W. Three-operator splitting for learning to predict equilibria in convex games. SIAM Journal on Mathematics of Data Science, 2024.
Han, F., Osher, S., and Li, W. Score-based neural ordinary differential equations for computing mean field control problems. Preprint, 2024.
F Han, S Osher, W Li, Convergence of Noise-Free Sampling Algorithms with Regularized Wasserstein Proximals. Preprint, 2024.
G Fu, S Osher, W Pazner, W Li, Generalized optimal transport and mean field control problems for reaction-diffusion systems with high-order finite element computation. Journal of Computational Physics, 2024.
Tibshirani, R. J., Fung, S. W., Heaton, H., and Osher, S. Laplace Meets Moreau: Smooth Approximation to Infimal Convolutions Using Laplace's Method. Preprint, 2024.
Heaton, H., Wu Fung, S., and Osher, S. Global solutions to nonconvex problems by evolution of Hamilton-Jacobi PDEs. Communications on Applied Mathematics and Computation, 2024.
Vidal, A., Fung, S. W., Osher, S., Tenorio, L., and Nurbekyan, L. Kernel Expansions for High-Dimensional Mean-Field Control with Non-local Interactions. Preprint, 2024.
Kang, Y., Zare, S., Lin, A., Han, Z., Osher, S., and Nguyen, H. Game Theory Meets Data Augmentation. IEEE Transactions on Artificial Intelligence, 2024.
Vijaywargiya, A., Fu, G., Osher, S., and Li, W. Efficient Computation of Mean field Control based Barycenters from Reaction-Diffusion Systems. Preprint, 2024.
Meng, T., Liu, S., Li, W., and Osher, S. A Primal-dual hybrid gradient method for solving optimal control problems and the corresponding Hamilton-Jacobi PDEs. Preprint, 2024.
Liu, S., Liu, S., Osher, S., and Li, W. A first-order computational algorithm for reaction-diffusion type equations via primal-dual hybrid gradient method. Journal of Computational Physics, 2024.
Zuo, X., Zhao, J., Liu, S., Osher, S., and Li, W. Numerical Analysis on Neural Network Projected Schemes for Approximating One Dimensional Wasserstein Gradient Flows. Preprint, 2024.
Zhang, B. J., Liu, S., Li, W., Katsoulakis, M. A., and Osher, S. J. Wasserstein proximal operators describe score-based generative models and resolve memorization. Preprint, 2024.
S Liu, X Zuo, S Osher, W Li, Numerical analysis of a first-order computational algorithm for reaction-diffusion equations via the primal-dual hybrid gradient method. Preprint, 2024.
G Fu, S Osher, W Li, High order spatial discretization for variational time implicit schemes: Wasserstein gradient flows and reaction-diffusion systems. Journal of Computational Physics, 2024.
Meng, T., Hao, W., Liu, S., Osher, S. J., and Li, W. Primal-dual hybrid gradient algorithms for computing time-implicit Hamilton-Jacobi equations. Preprint, 2024.
Nguyen, K., Hieu, N. M., Nguyen, V. D., Ho, N., Osher, S., and Nguyen, T. M. Revisiting over-smoothing and over-squashing using Ollivier-Ricci curvature. International Conference on Machine Learning, 2024.
Yu, J., Lai, R., Li, W., and Osher, S. Computational mean-field games on manifolds. Journal of Computational Physics, 2024.
Li, W., Liu, S., and Osher, S. Controlling conservation laws I: Entropy–entropy flux. Journal of Computational Physics, 2024.
Zuo, X., Osher, S., and Li, W. Primal-Dual Damping algorithms for optimization. Preprint, 2024.
Patil, P., Wu, Y., and Tibshirani, R. J. Failures and Successes of Cross-Validation for Early-Stopped Gradient Descent. International Conference on Artificial Intelligence and Statistics (AISTATS), 2024.
Lin, Y., Tabajara, L. M., and Vardi, M. Y. Dynamic Programming for Symbolic Boolean Realizability and Synthesis. Computer Aided Verification: 36th International Conference (CAV), 2024.
Angelopoulos, A., & Jordan, M.I., & Tibshirani, R.J. Gradient equilibrium in online learning: Theory and applications. Preprint, 2024.
Patil, P., Du, J-H., & Tibshirani, R.J. Revisiting optimism and model complexity in the wake of overparameterized machine learning. Preprint,2024.
Angelopoulos, A., Candès, E., & Tibshirani, R.J. Conformal PID control for time series prediction. Neural Information Processing Systems, 2023.
Ding, T., Angelopoulos, A., Bates, S., Jordan, M., & Tibshirani, R.J. Class-conditional conformal prediction with many classes. Neural Information Processing Systems, 2023.
Green, A., Balakrishnan, S., & Tibshirani, R.J. Minimax optimal regression over Sobolev spaces via Laplacian eigenmaps on neighborhood graphs. Information and Inference, 2023.
Hu, A., Green, A., & Tibshirani, R.J. The Voronoigram: Minimax estimation of bounded variation functions from scattered data. Preprint, 2023.
Luzi, L., Siahkoohi, A., Mayer, P.M., Casco-Rodriguez, J., & Baraniuk, R.G. Boomerang: Local sampling on image manifolds using diffusion models. Transactions on Machine Learning Research, 2024.
Dar, Y., LeJeune, D., & Baraniuk, R.G. The common intuition to transfer learning can win or lose: Case studies for linear regression. SIAM Journal on Mathematics of Data Science (SIMODS), 2024.
Roddenberry, M., Saragadam, V., Balakrishnan, G., & Baraniuk, R. G. Implicit Neural Representations and the Algebra of Complex Wavelets. International Conference on Learning Representations (ICLR), 2024.
Alemohammad, S., Casco-Rodriguez, J., Luzi, L., Humayun, A. I., Babaei, H., LeJeune, D., Siahkoohi, A., & Baraniuk, R. G. Self-Consuming Generative Models Go MAD. International Conference on Learning Representations (ICLR), 2024.
Luzi, L., LeJeune, D., Siahkoohi, A., Alemohammad, S., Saragadam, V., Babaei, H., Liu, N., Wang, Z., & Baraniuk, R. G. Titan: Bringing The Deep Image Prior to Implicit Representations. IEEE International Conference on Acoustics, Speech and Signal Processing, 2024.
Sonkar, S., Liu, L., Basu Mallick, D., & Baraniuk, R. G. Code Soliloquies for Accurate Calculations in Large Language Models. International Conference on Learning Analytics and Knowledge (LAK24), 2024.
Gama, F., Zilberstein, N., Sevilla, M., Baraniuk, R. G., & Segarra, S. Unsupervised Learning of Sampling Distributions for Particle Filters. IEEE Transactions on Signal Processing, 2023.
Nguyen, T., Ho, N., Patel, A., Anandkumar, A., Jordan, M., & Baraniuk, R. G. A Bayesian Perspective of Convolutional Neural Networks through a Deconvolutional Generative Model. Journal of Machine Learning Research, 2023.
Nguyen, T. M., Nguyen, T., Bui, L., Do, H., Nguyen, D. K., Le, D. D., Tran-The, H., Ho, N., Osher, S. J., & Baraniuk, R. G. A Probabilistic Framework for Pruning Transformers via a Finite Admixture of Keys. IEEE International Conference on Acoustics, Speech and Signal Processing, 2023.
Humayun, A. I., Balestriero, R., Balakrishnan, G., & Baraniuk, R. G. SplineCam: Exact Visualization of Deep Neural Network Geometry and Decision Boundaries. Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
Nguyen, T. M., Nguyen, T., Ho, N., Bertozzi, A. L., Baraniuk, R. G., & Osher, S. A Primal-Dual Framework for Transformers and Neural Networks. International Conference on Learning Representations (ICLR), 2023.
Tan, J., LeJeune, D., Mason, B., Javadi, H., & Baraniuk, R. G. A Blessing of Dimensionality in Membership Inference through Regularization. International Conference on Artificial Intelligence and Statistics (AISTATS), 2023.
Luzi, L., Ortiz Marrero, C., Wynar, N., Baraniuk, R. G., & Henry, M. J. Evaluating Generative Networks using Gaussian Mixtures of Image Features. Winter Conference on Applications of Computer Vision (WACV), 2023.
Nguyen, Tam, Nguyen M. Tan, and Richard Baraniuk .Mitigating Over-smoothing in Transformers via Regularized Nonlocal Functionals. Advances in Neural Information Processing Systems, 2023.
Arikan, T., Weiss, A., Vishnu, H., Deane, G., Singer, A., & Wornell, G. (2023, June). Learning Environmental Structure Using Acoustic Probes with a Deep Neural Network. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1-5). IEEE.
F Han, S Osher, W Li. Tensor Train Based Sampling Algorithms for Approximating Regularized Wasserstein Proximal Operators. arXiv preprint arXiv:2401.13125, 2024.
M Zhou, S Osher, W Li. A Deep Learning Algorithm for Computing Mean Field Control Problems via Forward-Backward Score Dynamics. arXiv preprint arXiv:2401.09547, 2024.
L Yang, SJ Osher. PDE Generalization of In-Context Operator Networks: A Study on 1D Scalar Nonlinear Conservation Laws. arXiv preprint arXiv:2401.07364, 2024.
L Yang, S Liu, T Meng, SJ Osher. In-Context Operator Learning with Data Prompts for Differential Equation Problems. Proceedings of the National Academy of Sciences, 120 (39), e2310142120, 2024.
HY Tan, S Osher, W Li. Noise-Free Sampling Algorithms via Regularized Wasserstein Proximals. arXiv preprint arXiv:2308.14945, 2023.
L Yang, T Meng, S Liu, SJ Osher. Prompting In-Context Operator Learning with Sensor Data, Equations, and Natural Language. arXiv preprint arXiv:2308.05061, 2023.
L Yang, S Liu, T Meng, SJ Osher. In-Context Operator Learning for Differential Equation Problems. Preprint, 2023.
W Li, S Liu, S Osher. A kernel formula for regularized Wasserstein proximal operators Research in the Mathematical Sciences 10 (4), 43
DeVore, Ronald, et al. Weighted variation spaces and approximation by shallow ReLU networks Applied and Computational Harmonic Analysis, 2024
J Shenouda, R Parhi, RD Nowak. A Continuous Transform for Localized Ridgelets IEEE International Conference on Sampling Theory and Applications (SampTA) 2023
J Shenouda, R Parhi, K Lee, RD Nowak Vector-Valued Variation Spaces and Width Bounds for DNNs: Insights on Weight Decay Regularization arXiv preprint arXiv:2305.16534
R Parhi and RD Nowak Deep Learning Meets Sparse Regularization: A signal processing perspective in IEEE Signal Processing Magazine, vol. 40, no. 6, pp. 63-74, Sept. 2023
L Yang, J Zhang, J Shenouda, D Papailiopoulos, K Lee, RD Nowak PathProx: A Proximal Gradient Algorithm for Weight Decay Regularized Deep Neural Networks. arXiv preprint arXiv:2210.03069
R Parhi and RD Nowak, Near-Minimax Optimal Estimation With Shallow ReLU Neural Networks in IEEE Transactions on Information Theory, vol. 69, no. 2, pp. 1125-1140, Feb. 2023
R Parhi and RD Nowak Banach Space Representer Theorems for Neural Networks
and Ridge Splines Journal of Machine Learning Research 2021
R Parhi and RD Nowak On Continuous-Domain Inverse Problems With Sparse Superpositions of Decaying Sinusoids as Solutions ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore, Singapore, 2022, pp. 5603-5607
Y Wen, N Jain, J Kirchenbauer, M Goldblum, J Geiping, T Goldstein, Hard Prompts Made Easy: Gradient-based Discrete Optimization for Prompt Tuning and Discovery in Advances in Neural Information Processing Systems 36, 2024, pp. 80.
Y Wen, J Kirchenbauer, J Geiping, T Goldstein, Tree-Rings Watermarks: Invisible Fingerprints for Diffusion Images in Advances in Neural Information Processing Systems 36
G Somepalli, V Singla, M Goldblum, J Geiping, T Goldstein, Understanding and Mitigating Copying in Diffusion Models in arXiv preprint arXiv:2305.20086.
J Kirchenbauer, J Geiping, Y Wen, J Katz, I Miers, T Goldstein, A Watermark for Large Language Models in arXiv preprint arXiv:2301.10226.
G Somepalli, V Singla, M Goldblum, J Geiping, T Goldstein, Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 119.
Shah, A., Roy, A., Shah, K., Mishra, S., Jacobs, D., Cherian, A., & Chellappa, R. (2023). HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Shah, A., Lundell, B., Sawhney, H., & Chellappa, R. (2023). STEPs: Self-Supervised Key Step Extraction from Unlabeled Procedural Videos. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)
Roy, A., Shah, A., Shah, K., Dhar, P., Cherian, A., & Chellappa, R. (2022). FeLMi: Few shot Learning with hard Mixup. In Advances in Neural Information Processing Systems (NeurIPS)
Pramanick, S., Han, G., Hou, R., Nag, S., Lim, S.-N., Ballas, N., Wang, Q., Chellappa, R., & Almahairi, A. (2024). Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Roy, A., Suin, M., Shah, A., Shah, K., Liu, J., & Chellappa, R. (n.d.). DiffNat: Improving diffusion image quality using natural image statistics, in arXiv preprint arXiv:2312.12423
Roy, A., Shah, A., Shah, K., Roy, A., & Chellappa, R. (n.d.). Cap2Aug: Caption guided Image-to-Image data Augmentation, in arXiv preprint arXiv:2212.0540
Wei, G., Wang, F., Shah, A., & Chellappa, R. (n.d.). Dual Prompt Tuning for Domain-Aware Federated Learning, in arXiv preprint arXiv:2310.0310
Goldblum, M., Tsipras, D., Xie, C., Chen, X., Schwarzschild, A., Song, D., Madry, A., Li, B., & Goldstein, T. Dataset security for machine learning: Data poisoning, backdoor attacks, and defenses. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022.
Gama, F., Zilberstein, N., Baraniuk, R. G., & Segarra, S. Unrolling Particles: Unsupervised Learning of Sampling Distributions, IEEE International Conference on Acoustics, Speech and Signal Processing – ICASSP’22, May 2022.
Sapoval, N., Aghazadeh, A., Nute, M. G., Antunes, D. A., Balaji, A., Baraniuk, R. G., Barberan, C. J., Dannenfelser, R., Dun, C., Edrisi, M., & Elworth, R. A. Current progress and open challenges for applying deep learning across the biosciences. Nature Communications, 13(1), pp.1-12, 2022.
Alemohammad, S., Babaei, H., Barberan, C. J., Liu, N., Luzi, L., Mason, B., & Baraniuk, R. G. NFT-K: Non-Fungible Tangent Kernels. IEEE International Conference on Acoustics, Speech and Signal Processing – ICASSP’22, May 2022.
Humayun, A. I., Balestriero, R., Kyrillidis, A., & Baraniuk, R. G. No More Than 6ft Apart: Robust K-Means via Radius Upper Bounds. IEEE International Conference on Acoustics, Speech and Signal Processing – ICASSP’22, May 2022.
Balestriero, R., Wang, Z., & Baraniuk, R. G. DeepHull: Fast Convex Hull Approximation in High Dimensions. IEEE International Conference on Acoustics, Speech and Signal Processing – ICASSP’22, May 2022.
Barberan, C. J., Alemohammad, S., Liu, N., Balestriero, R., & Baraniuk, R. G. NeuroView-RNN: It's About Time. FAccT, 2022.
Brenes, D., Barberan, C. J., Hunt, B., Parra, S. G., Salcedo, M. P., Possati-Resende, J. C., Cremer, M. L., Castle, P. E., Fregnani, J. H., Maza, M., & Schmeler, K. M. Multi-task network for automated analysis of high-resolution endomicroscopy images to detect cervical precancer and cancer, Computerized Medical Imaging and Graphics, 97, 2022.
Saragadam, V., Balestriero, R., Veeraraghavan, A., & Baraniuk, R. G. DeepTensor: Low-Rank Tensor Decomposition with Deep Network Priors. arXiv:2204.03145, 2022.
Dar, Y., LeJeune, D., & Baraniuk, R. G. The Common Intuition to Transfer Learning Can Win or Lose: Case Studies for Linear Regression. arXiv: 2103.05621v2, 2022.
Shrotri, A. A., Narodytska, N., Ignatiev, A., Meel, K. S., Marques-Silva, J., & Vardi, M. Y. Constraint-Driven Explanations for Black-Box ML Models. AAAI, 2022.
Patil, P., Rinaldo, A. & Tibshirani, R. J. Estimating functionals of the out-of-sample error distribution in high-dimensional ridge regression. AISTATS, 2022.
Li, W., Liu, S., & Osher, S. Controlling conservation laws II: Compressible Navier–Stokes equations. Journal of Computational Physics, 2022.
Humayun, A. I., Balestriero, R. & Baraniuk, R. G. Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022.
Humayun, A. I., Balestriero, R., & Baraniuk, R. G. Magnet: Uniform sampling from deep generative network manifolds without retraining. ICLR, 2022.
Saragadam, V., Tan, J., Balakrishnan, G., Baraniuk, R. G., & Veeraraghavan, A. MINER: Multiscale Implicit Neural Representations. arXiv:2202.03532, 2022.
Tibshirani, R. J. Divided Differences, Falling Factorials, and Discrete Splines: Another Look at Trend Filtering and Related Problems. Foundations and Trends in Machine Learning, Vol. 15, No. 6, 694-846, 2022.
Curry, M. J., Lyi, U., Goldstein, T., & Dickerson, J. P. Learning revenue-maximizing auctions with differentiable matching. AISTATS, 2022.
Riedi, R. H., Balestriero, R., & Baraniuk, R. G., Singular Value Perturbation and Deep Network Optimization, Constructive Approximation, 2022.
Lin, A.T., Debord, M., Estabridis, K., Hewer, G., Montufar, G., & Osher, S. Decentralized multi-agents by imitation of a centralized controller. In Mathematical and Scientific Machine Learning, PMLR. 2022.
Pramanick, S., Roy, A., & Patel, V. M. Multimodal Learning using Optimal Transport for Sarcasm and Humor Detection. Winter Conference on Computer Vision, 2022.
Tan, J., LeJeune, D., Mason, B., Javadi, H., & Baraniuk, R. G. Benign Overparameterization in Membership Inference with Early Stopping. arXiv:2205.14055, 2022.
Tan, J., Mason, B., Javadi, H., & Baraniuk, R. G. Parameters or Privacy: A Provable Tradeoff Between Overparameterization and Membership Inference. arXiv:2202.01243, 2022.
Baker, J., Xia, H., Wang, Y., Cherkaev, E., Narayan, A., Chen, L., Xin, J., Bertozzi, A. L., Osher, S. J., & Wang, B. Proximal Implicit ODE Solvers for Accelerating Learning Neural ODEs. arXiv:2204.0862, 2022.
Heaton, H., Fung, S. W., & Osher, S. Global Solutions to Nonconvex Problems by Evolution of Hamilton-Jacobi PDEs. arXiv:2202.11014, 2022.
Shah, A., Sra, S., Chellappa, R., Cherian, A. Max-Margin Contrastive Learning. AAAI, 2022.
Heaton, H., Fung, S. W., Lin, A.T., Osher, S., & Yin, W. Wasserstein-Based Projections with Applications to Inverse Problems. SIAM Journal on Mathematics of Data Science, 2022.
Green, A., Balakrishnan, S. & Tibshirani, R. J. Minimax Optimal Regression over Sobolev Spaces via Laplacian Eigenmaps on Neighborhood Graphs. arXiv:2111.07394, 2021.
Ni, R. Shu, M., Souri, H., Goldblum, M., & Goldstein, T. The Close Relationship Between Contrastive Learning and Meta-Learning. ICLR, 2021.
Barberan, C. J., Balestriero, R. & Baraniuk, R. G. NeuroView: Explainable Deep Network Decision Making, arXiv:2110.07778, 2021.
Saragadam, V., Dave, A., Veeraraghavan, A. & Baraniuk, R. G. Thermal Image Processing via Physics-Inspired Deep Networks. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021.
Shu, M., Wu, Z., Goldblum, M., & Goldstein, T. Encoding Robustness to Image Style via Adversarial Feature Perturbations. NeurIPS, 2021.
Schwarzschild, A., Borgnia, E., Gupta, A., Huang, F., Vishkin, U., Goldblum, M., & Goldstein, T. Can you learn an algorithm? generalizing from easy to hard problems with recurrent networks. NeurIPS, 2021.
Luzi, L., Marrero, C. O., Wynar, N., Baraniuk, R. G., & Henry, M. J. Evaluating generative networks using Gaussian mixtures of image features, arXiv:2110.05240, 2021.
Xia, H., Suliafu, V., Ji, H., Nguyen, T., Bertozzi, A. L., Osher, S., & Wang, B. Heavy ball neural ordinary differential equations. NeurIPS, 2021.
Nguyen, T., Suliafu, V., Osher, S., Chen, L., & Wang, B. Fmmformer: Efficient and flexible transformer via decomposed near-field and far-field attention. NeurIPS, 2021.
Li, W., Liu, S., & Osher, S. Controlling conservation laws I: entropy-entropy flux. arXiv:2111.05473, 2021.
Tan, J., Boominathan, V., Baraniuk, R. G., & Veeraraghavan, A. EDoF-ToF: Extended depth of field time-of-flight imaging. Optics Express, 29(23), 2021.
Fung, S. W., Heaton, H., Li, Q., McKenzie, D., Osher, S., & Yin, W. Efficient training of infinite-depth neural networks via Jacobian-Free backpropagation. AMS Fall Western Sectional Meeting, 2021.
Nguyen, T., Nguyen, T., Le, D., Nguyen, K., Tran, A., Baraniuk, R. G., Ho, N., & Osher, S. Improving transformers with probabilistic attention keys. ICML, 2021.
Wang, B., Xia, H., Nguyen, T., & Osher, S. How does momentum benefit deep neural networks architecture design? a few case studies. arXiv:2110.07034, 2021.
Thorpe, M., Nguyen, T. M., Xia, H., Strohmer, T., Bertozzi, A., Osher, S., & Wang, B. GRAND++: Graph neural diffusion with a source term. ICLR, 2021.
Lin, A. T., Fung, S. W., Li, W., Nurbekyan, L., & Osher, S. Alternating the population and control neural networks to solve high-dimensional stochastic mean-field games. Proceedings of the National Academy of Sciences (PNAS), 2021.
Lin, A. T., Li, W., Osher, S., & Montúfar, G. Wasserstein proximal of GANs. In International Conference on Geometric Science of Information, 2021.
Balestriero, R., & Baraniuk, R. G. Mad Max: Affine Spline Insights into Deep Learning. Proceedings of the IEEE (special issue on Advances in Machine Learning and Deep Neural Networks), 2021.
Baraniuk, R. G., Donoho, L., & Gavish, M. The Science of Deep Learning. Proceedings of the National Academy of Sciences (PNAS), PNAS:117:48:30029, 2020.
Ongie, G., Jalal, A., Metzler, C. A., Baraniuk, R. G., Dimakis, A. G., & Willett, R. Deep Learning Techniques for Inverse Problems in Imaging. IEEE Journal on Selected Topics in Information Theory (inaugural issue), 2020.
Lejeune, D., Javadi, H., & Baraniuk, R. G. The Flip Side of the Reweighted Coin: Duality of Adaptive Dropout and Regularization. NeurIPS, 2021.
Chaudhri, V. K., Boggess, M., Aung, H. L., Basu Mallick, D., Waters, A. C., & Baraniuk, R. G. Bootstrapping Ontology Graphs. Automated Knowledge Base Construction, 2021.
Alemohammad, S., Balestriero, R., Wang, J., & Baraniuk, R. G. The Recurrent Neural Tangent Kernel. ICLR, 2021.
Yao, T., LeJeune, D., Javadi, H., Baraniuk, R. G., & Allen, G. A. Minipatch Learning as Implicit Ridge- Like Regularization. IEEE International Conference on Big Data and Smart Computing, 2021.
Balestriero, R., Paris, S., & Baraniuk, R. G. Analytical Probability Distributions and EM-Learning for Deep Generative Networks. NeurIPS, 2020.
Nguyen, T. M., Ho, N., Patel, A., Anandkumar A., Jordan, M., & Baraniuk, R. G. A Bayesian Perspective of Convolutional Neural Networks through a Deconvolutional Generative Model. submitted to Journal of Machine Learning Research, arXiv preprint arxiv:1811.02657, 2020.
Dar, Y. and Baraniuk, R. G. Double Double Descent: On Generalization Errors in Transfer Learning between LInear Regression Tasks. arXiv preprint arXiv:2006.07002, 2021.
Luzi, L., Dar, Y., & Baraniuk, R. Double Descent and Other Interpolation Phenomena in GANs. arXiv preprint arXiv:2106.04003, 2021.
Dar, Y., Muthukumar, V. & Baraniuk, R. G. A farewell to the bias-variance tradeoff? an overview of the theory of overparameterized machine learning. arXiv:2109.02355, 2021.
Kota, P. K., LeJeune, D., Drezek, R. A., & Baraniuk, R. G. Extreme Compressed Sensing of Poisson Rates from Multiple Measurements. arXiv preprint arXiv:2103.08711, 2021.
Green, A., Balakrishnan, S., Tibshirani, R. Minimax Optimal Regression over Sobolev Spaces via Laplacian Regularization on Neighborhood Graphs. Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, PMLR 130:2602-2610, 2021.
Patik, P., Wei, Y., Rinaldo, A., Tibshirani, R. Uniform Consistency of Cross-Validation Estimators for High-Dimensional Ridge Regression. Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, PMLR 130:3178-3186, 2021.
Goldblum, M., Reich, S., Fowl, L., Ni, R., Cherepanova, V., & Goldstein, T. Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks. ICML 2020, arXiv preprint arXiv:2002.06753, 2020.
Huang, W., Emam, Z., Goldblum, M., Fowl, L., Terry, J.K., Huang, F., & Goldstein, T. Understanding Generalization through Visualizations. arXiv preprint arXiv:1906.03291, 2019.
Pope, P., Zhu, C., Abdelkader, A., Goldblum, M., & Goldstein, T. The Intrinsic Dimension of Images and Its Impact on Learning. ICLR, 2020.
Sankararaman, K. A., De, So., Xu, Z., Huang, W. R., & Goldstein, T. The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent. ICML, 2020.
Parhi, R. and Nowak, R. What Kinds of Functions do Deep Neural Networks Learn? Insights from Variational Spline Theory. arXiv preprint arXiv:2105.03361, 2021.
Daubechies, I., DeVore, R., Foucart, S., Hanin, B., & Petrova, G. Nonlinear Approximation and (Deep) ReLU Networks. arXiv preprint arXiv:1905.02199, 2020.
DeVore, R., Hanin, B., & Petrova, G. Neural Network Approximation. arXiv preprint arXiv:2012.14501, 2020.
Shah, A., Mishra, S., Bansal, A., Chen, J.C., Chellappa, R., & Srivastava, A. Pose And Joint-Aware Action Recognition. Winter Conference on Computer Vision, 2022.
Pramanick, S., Roy, A., & Patel, V.M, Multimodal Learning using Optimal Transport for Sarcasm and Humor Detection. Winter Conference on Computer Vision, 2022.
Nguyen, T. M., Baraniuk, R. G., Bertozzi, A., Osher, S., & Wang, B. MomentumRNN: Integrating Momentum into Recurrent Neural Networks. NeurIPS, 2020.
Nguyen, T. M., Suliafu, V., Osher, S. J., Chen, L., & Wang, B. FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention. NeurIPS, 2021.
Xia, H., Suliafu, V., Ji, H., Nguyen, T. M., Bertozzi, A. L., Osher, S. J., & Wang, B. Heavy Ball Neural Ordinary Differential Equations. NeurIPS, 2021.
Wang, B., Nguyen, T. M., Bertozzi, A. L., Baraniuk, R. G., & Osher, S. J. Scheduled Restart Momentum for Accelerated Stochastic Gradient Descent. arXiv preprint arXiv:2002.10583, 2020.
Kyrillidis, A., Shrivastava, A., Vardi, M. Y., & Zhang Z. Solving Hybrid Boolean Constraints in Continuous Space via Multilinear Fourier Expansions. Artif. Intell. 299: 103559, 2021.
Kyrillidis, A., Vardi M. Y., Zhang, Z. On Continuous Local BDD-Based Search for Hybrid SAT Solving. AAAI: 3841-3850, 2021.
Dudek, J. M., Phan, V. H, N., & Vardi, M. Y. ProCount: Weighted Projected Model Counting with Graded Project-Join Trees. SAT: 152-170, 2021.