Papers
The alignment property of SGD noise and how it helps select flat minima: A stability analysis
Lei Wu, Mingze Wang, Weijie Su
The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset
Hugo Laurençon, Lucile Saulnier, Thomas Wang et al.
The Burer-Monteiro SDP method can fail even above the Barvinok-Pataki bound
Liam O'Carroll, Vaidehi Srinivas, Aravindan Vijayaraghavan
The computational and learning benefits of Daleian neural networks
Adam Haber, Elad Schneidman
The Curse of Unrolling: Rate of Differentiating Through Optimization
Damien Scieur, Gauthier Gidel, Quentin Bertrand et al.
The Dollar Street Dataset: Images Representing the Geographic and Socioeconomic Diversity of the World
William Gaviria Rojas, Sudnya Diamos, Keertan Kini et al.
The Effects of Regularization and Data Augmentation are Class Dependent
Randall Balestriero, Leon Bottou, Yann LeCun
The First Optimal Acceleration of High-Order Methods in Smooth Convex Optimization
Dmitry Kovalev, Alexander Gasnikov
The First Optimal Algorithm for Smooth and Strongly-Convex-Strongly-Concave Minimax Optimization
Dmitry Kovalev, Alexander Gasnikov
The Franz-Parisi Criterion and Computational Trade-offs in High Dimensional Statistics
Afonso S Bandeira, Ahmed El Alaoui, Samuel Hopkins et al.
The Gyro-Structure of Some Matrix Manifolds
Xuan Son Nguyen
The Hessian Screening Rule
Johan Larsson, Jonas Wallin
The Impact of Task Underspecification in Evaluating Deep Reinforcement Learning
Vindula Jayawardana, Catherine Tang, Sirui Li et al.
The Implicit Delta Method
Nathan Kallus, James McInerney
The least-control principle for local learning at equilibrium
Alexander Meulemans, Nicolas Zucchet, Seijin Kobayashi et al.
The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning
Zixin Wen, Yuanzhi Li
The Minority Matters: A Diversity-Promoting Collaborative Metric Learning Algorithm
Shilong Bao, Qianqian Xu, Zhiyong Yang et al.
The Missing Invariance Principle found -- the Reciprocal Twin of Invariant Risk Minimization
Dongsung Huh, Avinash Baidya
The Nature of Temporal Difference Errors in Multi-step Distributional Reinforcement Learning
Yunhao Tang, Remi Munos, Mark Rowland et al.
The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization
Mufan Li, Mihai Nica, Dan Roy
The Neural Testbed: Evaluating Joint Predictions
Ian Osband, Zheng Wen, Seyed Mohammad Asghari et al.
Theoretical analysis of deep neural networks for temporally dependent observations
Mingliang Ma, Abolfazl Safikhani
Theoretically Better and Numerically Faster Distributed Optimization with Smoothness-Aware Quantization Techniques
Bokun Wang, Mher Safaryan, Peter Richtarik
Theoretically Provable Spiking Neural Networks
Shao-Qun Zhang, Zhi-Hua Zhou
Theory and Approximate Solvers for Branched Optimal Transport with Multiple Sources
Peter Lippmann, Enrique Fita Sanmartín, Fred A. Hamprecht