conftrace_
← Optimization & Theory
Machine Learning › Optimization & Theory ›

Learning Theory

5,312 papers

Papers per year

Papers

Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction NIPS 2021
Analytic Insights into Structure and Rank of Neural Network Hessian Maps NIPS 2021
Efficiently Learning One Hidden Layer ReLU Networks From Queries NIPS 2021
Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation NIPS 2021
On the Power of Differentiable Learning versus PAC and SQ Learning NIPS 2021
RL for Latent MDPs: Regret Guarantees and a Lower Bound NIPS 2021
Understanding Bandits with Graph Feedback NIPS 2021
Information-theoretic generalization bounds for black-box learning algorithms NIPS 2021
Causal Bandits with Unknown Graph Structure NIPS 2021
Local Signal Adaptivity: Provable Feature Learning in Neural Networks Beyond Kernels NIPS 2021
Never Go Full Batch (in Stochastic Convex Optimization) NIPS 2021
Counterfactual Maximum Likelihood Estimation for Training Deep Networks NIPS 2021
Closing the Gap: Tighter Analysis of Alternating Stochastic Gradient Methods for Bilevel Problems NIPS 2021
Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification NIPS 2021
Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis NIPS 2021
Identification of the Generalized Condorcet Winner in Multi-dueling Bandits NIPS 2021
Optimizing Information-theoretical Generalization Bound via Anisotropic Noise of SGLD NIPS 2021
A Mathematical Framework for Quantifying Transferability in Multi-source Transfer Learning NIPS 2021
Towards Context-Agnostic Learning Using Synthetic Data NIPS 2021
Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers NIPS 2021
Towards a Unified Information-Theoretic Framework for Generalization NIPS 2021
On the Algorithmic Stability of Adversarial Training NIPS 2021
Towards Sharper Generalization Bounds for Structured Prediction NIPS 2021
Teaching via Best-Case Counterexamples in the Learning-with-Equivalence-Queries Paradigm NIPS 2021
The staircase property: How hierarchical structure can guide deep learning NIPS 2021