← Optimization & Theory
Machine Learning › Optimization & Theory ›

Learning Theory

5312 directly classified papers

Papers per year

Papers

Support Recovery for Orthogonal Matching Pursuit: Upper and Lower bounds NIPS 2018
On Oracle-Efficient PAC RL with Rich Observations NIPS 2018
Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes NIPS 2018
Fast Rates of ERM and Stochastic Approximation: Adaptive to Error Bound Conditions NIPS 2018
How Many Samples are Needed to Estimate a Convolutional Neural Network? NIPS 2018
Near-Optimal Time and Sample Complexities for Solving Markov Decision Processes with a Generative Model NIPS 2018
PAC-learning in the presence of adversaries NIPS 2018
Evaluating Historical Text Normalization Systems: How Well Do They Generalize? NAACL 2018
Tight Bounds for Bandit Combinatorial Optimization COLT 2017
Lower bounds on the robustness to adversarial perturbations NIPS 2017
SGD Learns the Conjugate Kernel Class of the Network NIPS 2017
A Learning Theory of Ranking Aggregation AISTATS 2017
Sketching Meets Random Projection in the Dual: A Provable Recovery Algorithm for Big and High-dimensional Data AISTATS 2017
Eigenvalue Decay Implies Polynomial-Time Learnability for Neural Networks NIPS 2017
SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability NIPS 2017
Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inference NIPS 2017
Optimal learning via local entropies and sample compression COLT 2017
On the Consistency of Ordinal Regression Methods JMLR 2017
Analyzing Tensor Power Method Dynamics in Overcomplete Regime JMLR 2017
Bridging Supervised Learning and Test-Based Co-optimization JMLR 2017
Empirical Risk Minimization for Stochastic Convex Optimization: $O(1/n)$- and $O(1/n^2)$-type of Risk Bounds COLT 2017
On Learning vs. Refutation COLT 2017
On Equivalence of Martingale Tail Bounds and Deterministic Regret Inequalities COLT 2017
Online Learning Without Prior Information COLT 2017
Towards Instance Optimal Bounds for Best Arm Identification COLT 2017