learning theory

On the Impossibility of Learning to Cooperate with Adaptive Partner Strategies in Repeated Games ICML 2022 On the non-universality of deep learning: quantifying the cost of symmetry NeurIPS 2022 On the Optimality Gap of Warm-Started Hyperparameter Optimization AutoML 2022 On the Optimal Memorization Power of ReLU Neural Networks ICLR 2022 On the Statistical Benefits of Curriculum Learning ICML 2022 On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL NeurIPS 2022 Open Problem: Do you pay for Privacy in Online learning? COLT 2022 Open Problem: Properly learning decision trees in polynomial time? COLT 2022 Optimal SQ Lower Bounds for Learning Halfspaces with Massart Noise COLT 2022 Overparameterization from Computational Constraints NeurIPS 2022 PAC Top-k Identification under SST in Limited Rounds AISTATS 2022 Phase transitions in when feedback is useful NeurIPS 2022 Provable Lifelong Learning of Representations AISTATS 2022 Realizable Learning is All You Need COLT 2022 Regularized Modal Regression on Markov-Dependent Observations: A Theoretical Assessment AAAI 2022 Resonance in Weight Space: Covariate Shift Can Drive Divergence of SGD with Momentum ICLR 2022 Rethinking Influence Functions of Neural Networks in the Over-Parameterized Regime AAAI 2022 Robust Model Selection and Nearly-Proper Learning for GMMs NeurIPS 2022 Shallow and Deep Networks are Near-Optimal Approximators of Korobov Functions ICLR 2022 Spectral Bias Outside the Training Set for Deep Networks in the Kernel Regime NeurIPS 2022 SQ Lower Bounds for Learning Single Neurons with Massart Noise NeurIPS 2022 Stability and Generalization for Markov Chain Stochastic Gradient Methods NeurIPS 2022 Stability of SGD: Tightness analysis and improved bounds UAI 2022 Structural Analysis of Branch-and-Cut and the Learnability of Gomory Mixed Integer Cuts NeurIPS 2022 Theoretical analysis of deep neural networks for temporally dependent observations NeurIPS 2022