← Optimization & Theory
Machine Learning › Optimization & Theory ›

Theory

4950 directly classified papers

Papers per year

Papers

Experimental Designs for Heteroskedastic Variance NIPS 2023
On permutation symmetries in Bayesian neural network posteriors: a variational perspective NIPS 2023
A Unifying Perspective on Multi-Calibration: Game Dynamics for Multi-Objective Learning NIPS 2023
One-step differentiation of iterative algorithms NIPS 2023
On Robust Streaming for Learning with Experts: Algorithms and Lower Bounds NIPS 2023
A Fractional Graph Laplacian Approach to Oversmoothing NIPS 2023
Investigating how ReLU-networks encode symmetries NIPS 2023
A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphs NIPS 2023
Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension NIPS 2023
Window-Based Distribution Shift Detection for Deep Neural Networks NIPS 2023
The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks NIPS 2023
When Do Graph Neural Networks Help with Node Classification? Investigating the Homophily Principle on Node Distinguishability NIPS 2023
(Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy NIPS 2023
Causal Component Analysis NIPS 2023
Demystifying Oversmoothing in Attention-Based Graph Neural Networks NIPS 2023
PAC-Bayesian Spectrally-Normalized Bounds for Adversarially Robust Generalization NIPS 2023
Isometric Quotient Variational Auto-Encoders for Structure-Preserving Representation Learning NIPS 2023
A Rigorous Link between Deep Ensembles and (Variational) Bayesian Methods NIPS 2023
Critical Initialization of Wide and Deep Neural Networks using Partial Jacobians: General Theory and Applications NIPS 2023
What Makes Data Suitable for a Locally Connected Neural Network? A Necessary and Sufficient Condition Based on Quantum Entanglement. NIPS 2023
Limits, approximation and size transferability for GNNs on sparse graphs via graphops NIPS 2023
Training Neural Networks is NP-Hard in Fixed Dimension NIPS 2023
On the Convergence of Black-Box Variational Inference NIPS 2023
Fine-grained Expressivity of Graph Neural Networks NIPS 2023
Neural Oscillators are Universal NIPS 2023