David J. Schwab

43 papers A* 9A 1Journal 31Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Soft Quantization: Model Compression Via Weight Coupling. CoRR Daniel T. Bernstein, Luca di Carlo, David J. Schwab
2026	J	`jnl`	Stochastic Resetting Accelerates Policy Convergence in Reinforcement Learning. CoRR Jello Zhou, Vudtiwat Ngampruetikorn, David J. Schwab
2025	J	`jnl`	Data coarse graining can improve model performance. CoRR Alex Nguyen, David J. Schwab, Vudtiwat Ngampruetikorn
2025	J	`jnl`	Entropic Confinement and Mode Connectivity in Overparameterized Neural Networks. CoRR Luca di Carlo, Chase Goddard, David J. Schwab
2025	J	`jnl`	Understanding temperature tuning in energy-based models. CoRR Peter W. Fields, Vudtiwat Ngampruetikorn, David J. Schwab, Stephanie E. Palmer
2025	A*	`conf`	When can in-context learning generalize out of task distribution? ICML Page C. Goddard, Lindsay M. Smith, Vudtiwat Ngampruetikorn, David J. Schwab
2025	J	`jnl`	When can in-context learning generalize out of task distribution? CoRR Page C. Goddard, Lindsay M. Smith, Vudtiwat Ngampruetikorn, David J. Schwab
2024	J	`jnl`	Generalization vs. Specialization under Concept Shift. CoRR Alex Nguyen, David J. Schwab, Vudtiwat Ngampruetikorn
2023	A*	`conf`	Don't forget the nullspace! Nullspace occupancy as a mechanism for out of distribution failure. ICLR Daksh Idnani, Vivek Madan, Naman Goyal, David J. Schwab, Ramakrishna Vedantam
2023	J	`jnl`	Generalized Information Bottleneck for Gaussian Variables. CoRR Vudtiwat Ngampruetikorn, David J. Schwab
2023	J	`jnl`	Random-Energy Secret Sharing via Extreme Synergy. CoRR Vudtiwat Ngampruetikorn, David J. Schwab
2022	A*	`conf`	Information bottleneck theory of high-dimensional regression: relevancy, efficiency and optimality. NeurIPS Vudtiwat Ngampruetikorn, David J. Schwab
2022	J	`jnl`	Information bottleneck theory of high-dimensional regression: relevancy, efficiency and optimality. CoRR Vudtiwat Ngampruetikorn, David J. Schwab
2021	A*	`conf`	An Empirical Investigation of Domain Generalization with Empirical Risk Minimizers. NeurIPS Ramakrishna Vedantam, David Lopez-Paz, David J. Schwab
2021	J	`jnl`	Leveraging background augmentations to encourage semantic focus in self-supervised contrastive learning. CoRR Chaitanya K. Ryali, David J. Schwab, Ari S. Morcos
2021	A*	`conf`	Perturbation Theory for the Information Bottleneck. NeurIPS Vudtiwat Ngampruetikorn, David J. Schwab
2021	J	`jnl`	Perturbation Theory for the Information Bottleneck. CoRR Vudtiwat Ngampruetikorn, David J. Schwab
2021	A*	`conf`	Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs. ICLR Jonathan Frankle, David J. Schwab, Ari S. Morcos
2020	J	`jnl`	Are all negatives created equal in contrastive instance discrimination? CoRR Tiffany Tianhui Cai, Jonathan Frankle, David J. Schwab, Ari S. Morcos
2020	—	`conf`	Gating creates slow modes and controls phase-space complexity in GRUs and LSTMs. MSML Tankut Can, Kamesh Krishnamurthy, David J. Schwab
2020	J	`jnl`	Gating creates slow modes and controls phase-space complexity in GRUs and LSTMs. CoRR Tankut Can, Kamesh Krishnamurthy, David J. Schwab
2020	A*	`conf`	Learning Optimal Representations with the Decodable Information Bottleneck. NeurIPS Yann Dubois, Douwe Kiela, David J. Schwab, Ramakrishna Vedantam
2020	J	`jnl`	Learning Optimal Representations with the Decodable Information Bottleneck. CoRR Yann Dubois, Douwe Kiela, David J. Schwab, Ramakrishna Vedantam
2020	J	`jnl`	Nonequilibrium Statistical Mechanics of Continuous Attractors. Neural Comput. Weishun Zhong, Zhiyue Lu, David J. Schwab, Arvind Murugan
2020	A*	`conf`	The Early Phase of Neural Network Training. ICLR Jonathan Frankle, David J. Schwab, Ari S. Morcos
2020	J	`jnl`	The Early Phase of Neural Network Training. CoRR Jonathan Frankle, David J. Schwab, Ari S. Morcos
2020	J	`jnl`	Theory of gating in recurrent neural networks. CoRR Kamesh Krishnamurthy, Tankut Can, David J. Schwab
2020	J	`jnl`	Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs. CoRR Jonathan Frankle, David J. Schwab, Ari S. Morcos
2019	J	`jnl`	How noise affects the Hessian spectrum in overparameterized neural networks. CoRR Mingwei Wei, David J. Schwab
2019	J	`jnl`	Mean-field Analysis of Batch Normalization. CoRR Mingwei Wei, James Stokes, David J. Schwab
2019	J	`jnl`	The Information Bottleneck and Geometric Clustering. Neural Comput. DJ Strouse, David J. Schwab
2018	J	`jnl`	A high-bias, low-variance introduction to Machine Learning for physicists. CoRR Pankaj Mehta, Marin Bukov, Ching-Hao Wang, Alexandre G. R. Day, Clint Richardson, Charles K. Fisher, David J. Schwab
2018	A*	`conf`	Learning to Share and Hide Intentions using Information Regularization. NeurIPS Daniel Strouse, Max Kleiman-Weiner, Josh Tenenbaum, Matthew M. Botvinick, David J. Schwab
2018	J	`jnl`	Learning to Share and Hide Intentions using Information Regularization. CoRR DJ Strouse, Max Kleiman-Weiner, Josh Tenenbaum, Matthew M. Botvinick, David J. Schwab
2017	J	`jnl`	The Deterministic Information Bottleneck. Neural Comput. DJ Strouse, David J. Schwab
2017	J	`jnl`	The information bottleneck and geometric clustering. CoRR DJ Strouse, David J. Schwab
2016	J	`jnl`	Comment on "Why does deep and cheap learning work so well?" [arXiv: 1608.08225]. CoRR David J. Schwab, Pankaj Mehta
2016	J	`jnl`	Supervised Learning with Quantum-Inspired Tensor Networks. CoRR E. Miles Stoudenmire, David J. Schwab
2016	—	`conf`	Supervised Learning with Tensor Networks. NIPS Edwin Miles Stoudenmire, David J. Schwab
2016	A	`conf`	The Deterministic Information Bottleneck. UAI DJ Strouse, David J. Schwab
2016	J	`jnl`	The deterministic information bottleneck. CoRR DJ Strouse, David J. Schwab
2014	J	`jnl`	An exact mapping between the Variational Renormalization Group and Deep Learning. CoRR Pankaj Mehta, David J. Schwab
2014	J	`jnl`	Quantifying the Role of Population Subdivision in Evolution on Rugged Fitness Landscapes. PLoS Comput. Biol. Anne-Florence Bitbol, David J. Schwab