Co-occurring keywords · papers mentioning both
Papers
On Convergence in Wasserstein Distance and f-divergence Minimization Problems
AISTATS 2024
On Differentially Private Subspace Estimation in a Distribution-Free Setting
NeurIPS 2024
One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
NeurIPS 2024
One-Step Forward and Backtrack: Overcoming Zig-Zagging in Loss-Aware Quantization Training
AAAI 2024
One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention
ICLR 2024
On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability
NeurIPS 2024
On Partial Optimal Transport: Revising the Infeasibility of Sinkhorn and Efficient Gradient Methods
AAAI 2024
On the Hardness of Online Nonconvex Optimization with Single Oracle Feedback
ICLR 2024
On the Hardness of Probabilistic Neurosymbolic Learning
ICML 2024
On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory
NeurIPS 2024
On the Nyström Approximation for Preconditioning in Kernel Machines
AISTATS 2024
On the Origins of Linear Representations in Large Language Models
ICML 2024
On the Power of Small-size Graph Neural Networks for Linear Programming
NeurIPS 2024
On the Saturation Effects of Spectral Algorithms in Large Dimensions
NeurIPS 2024
On the Stability and Generalization of Meta-Learning
NeurIPS 2024
On the Unstable Convergence Regime of Gradient Descent
AAAI 2024
On Tractable Φ-Equilibria in Non-Concave Games
NeurIPS 2024
Open Problem: Anytime Convergence Rate of Gradient Descent
COLT 2024
Optimal First-Order Algorithms as a Function of Inequalities
JMLR 2024
Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs
EMNLP 2024
Parameter-Agnostic Optimization under Relaxed Smoothness
AISTATS 2024
Parameter-free Clipped Gradient Descent Meets Polyak
NeurIPS 2024
Performative Control for Linear Dynamical Systems
NeurIPS 2024
Plug-and-Play image restoration with Stochastic deNOising REgularization
ICML 2024
Position: Do pretrained Transformers Learn In-Context by Gradient Descent?
ICML 2024