Theory

Proving Linear Mode Connectivity of Neural Networks via Optimal Transport AISTATS 2024 Rethinking Robustness of Model Attributions AAAI 2024 Revisiting the Information Capacity of Neural Network Watermarks: Upper Bound Estimation and Beyond AAAI 2024 Robust Image Denoising through Adversarial Frequency Mixup CVPR 2024 ScalingFilter: Assessing Data Quality through Inverse Utilization of Scaling Laws EMNLP 2024 Scaling Law for Time Series Forecasting NeurIPS 2024 Scaling Laws Across Model Architectures: A Comparative Analysis of Dense and MoE Models in Large Language Models EMNLP 2024 Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations NeurIPS 2024 Scaling Laws for Data Filtering-- Data Curation cannot be Compute Agnostic CVPR 2024 Scaling Laws for Fact Memorization of Large Language Models EMNLP 2024 Scaling Laws in Linear Regression: Compute, Parameters, and Data NeurIPS 2024 Scaling Parameter-Constrained Language Models with Quality Data EMNLP 2024 Score-based generative models are provably robust: an uncertainty quantification perspective NeurIPS 2024 Separation and Bias of Deep Equilibrium Models on Expressivity and Learning Dynamics NeurIPS 2024 Separations in the Representational Capabilities of Transformers and Recurrent Architectures NeurIPS 2024 SGD vs GD: Rank Deficiency in Linear Networks NeurIPS 2024 Simplicity Bias in Overparameterized Machine Learning AAAI 2024 Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning NeurIPS 2024 SMR: State Memory Replay for Long Sequence Modeling ACL 2024 Spectrum Extraction and Clipping for Implicitly Linear Layers AISTATS 2024 Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes NeurIPS 2024 Stepping on the Edge: Curvature Aware Learning Rate Tuners NeurIPS 2024 StreamingFlow: Streaming Occupancy Forecasting with Asynchronous Multi-modal Data Streams via Neural Ordinary Differential Equation CVPR 2024 Structured Gradient-based Interpretations via Norm-Regularized Adversarial Training CVPR 2024 SVARM-IQ: Efficient Approximation of Any-order Shapley Interactions through Stratification AISTATS 2024