Learning Theory

Size and Depth Separation in Approximating Benign Functions with Neural Networks COLT 2021 Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction NeurIPS 2021 Smooth Bandit Optimization: Generalization to Holder Space AISTATS 2021 Softmax Policy Gradient Methods Can Take Exponential Time to Converge COLT 2021 Speedy Performance Estimation for Neural Architecture Search NeurIPS 2021 Spherical Motion Dynamics: Learning Dynamics of Normalized Neural Network using SGD and Weight Decay NeurIPS 2021 Stability and Deviation Optimal Risk Bounds with Convergence Rate $O(1/n)$ NeurIPS 2021 Stability and Generalization for Randomized Coordinate Descent IJCAI 2021 Stability and Generalization of Bilevel Programming in Hyperparameter Optimization NeurIPS 2021 Stability and Generalization of Decentralized Stochastic Gradient Descent AAAI 2021 Stability and Generalization of Stochastic Gradient Methods for Minimax Problems ICML 2021 Stability and Risk Bounds of Iterative Hard Thresholding AISTATS 2021 Stability & Generalisation of Gradient Descent for Shallow Neural Networks without the Neural Tangent Kernel NeurIPS 2021 Stable Sample Compression Schemes: New Applications and an Optimal SVM Margin Bound ALT 2021 Statistical Query Algorithms and Low Degree Tests Are Almost Equivalent COLT 2021 Statistical Query Lower Bounds for List-Decodable Linear Regression NeurIPS 2021 Statistical Query Lower Bounds for Tensor PCA JMLR 2021 Statistical Undecidability in Linear, Non-Gaussian Causal Models in the Presence of Latent Confounders NeurIPS 2021 Stochastic bandits with groups of similar arms. NeurIPS 2021 Stochastic Gradient Descent Meets Distribution Regression AISTATS 2021 Stochastic Graphical Bandits with Adversarial Corruptions AAAI 2021 Stochastic Linear Bandits Robust to Adversarial Attacks AISTATS 2021 Stochastic Multi-Armed Bandits with Unrestricted Delay Distributions ICML 2021 Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret NeurIPS 2021 Strategically efficient exploration in competitive multi-agent reinforcement learning UAI 2021