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

Learning Theory

5,334 papers

Papers per year

17
66
123
466
307
'05
'10
'15
'20
'25

Papers

Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality NIPS 2024
A Theory of Optimistically Universal Online Learnability for General Concept Classes NIPS 2024
Graph Convolutions Enrich the Self-Attention in Transformers! NIPS 2024
Understanding Emergent Abilities of Language Models from the Loss Perspective NIPS 2024
Learning via Surrogate PAC-Bayes NIPS 2024
Provable Tempered Overfitting of Minimal Nets and Typical Nets NIPS 2024
Only Strict Saddles in the Energy Landscape of Predictive Coding Networks? NIPS 2024
Dissecting Query-Key Interaction in Vision Transformers NIPS 2024
How does Inverse RL Scale to Large State Spaces? A Provably Efficient Approach NIPS 2024
Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs NIPS 2024
Rethinking LLM Memorization through the Lens of Adversarial Compression NIPS 2024
The Price of Implicit Bias in Adversarially Robust Generalization NIPS 2024
Algorithmic progress in language models NIPS 2024
Sample and Computationally Efficient Robust Learning of Gaussian Single-Index Models NIPS 2024
Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation NIPS 2024
Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit NIPS 2024
Robust Offline Active Learning on Graphs NIPS 2024
Wide Two-Layer Networks can Learn from Adversarial Perturbations NIPS 2024
On the Limitations of Fractal Dimension as a Measure of Generalization NIPS 2024
Multiclass Transductive Online Learning NIPS 2024
Scaling Laws in Linear Regression: Compute, Parameters, and Data NIPS 2024
How Do Large Language Models Acquire Factual Knowledge During Pretraining? NIPS 2024
A Canonicalization Perspective on Invariant and Equivariant Learning NIPS 2024
Learning Cut Generating Functions for Integer Programming NIPS 2024
Worst-Case Offline Reinforcement Learning with Arbitrary Data Support NIPS 2024