Optimization

Sinkhorn Flow as Mirror Flow: A Continuous-Time Framework for Generalizing the Sinkhorn Algorithm AISTATS 2024 Sketching for Distributed Deep Learning: A Sharper Analysis NeurIPS 2024 Sliced Wasserstein with Random-Path Projecting Directions ICML 2024 Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models CVPR 2024 Soft ascent-descent as a stable and flexible alternative to flooding NeurIPS 2024 SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training ACL 2024 SOI: Scaling Down Computational Complexity by Estimating Partial States of the Model NeurIPS 2024 Solving Attention Kernel Regression Problem via Pre-conditioner AISTATS 2024 SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning EMNLP 2024 Space-Time Continuous PDE Forecasting using Equivariant Neural Fields NeurIPS 2024 Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration NeurIPS 2024 SS1: Accelerating Inference with Fast and Expressive Sketch Structured Transform NeurIPS 2024 ST$_k$: A Scalable Module for Solving Top-k Problems NeurIPS 2024 Stability and Generalizability in SDE Diffusion Models with Measure-Preserving Dynamics NeurIPS 2024 Stable Language Model Pre-training by Reducing Embedding Variability EMNLP 2024 Stepping Forward on the Last Mile NeurIPS 2024 Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution NeurIPS 2024 Stochastic Methods in Variational Inequalities: Ergodicity, Bias and Refinements AISTATS 2024 Stochastic Modified Flows, Mean-Field Limits and Dynamics of Stochastic Gradient Descent JMLR 2024 Stochastic Newton Proximal Extragradient Method NeurIPS 2024 Straight-Through Meets Sparse Recovery: the Support Exploration Algorithm ICML 2024 Structured Inverse-Free Natural Gradient Descent: Memory-Efficient & Numerically-Stable KFAC ICML 2024 SURE: SUrvey REcipes for building reliable and robust deep networks CVPR 2024 Swift Sampler: Efficient Learning of Sampler by 10 Parameters NeurIPS 2024 SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention NeurIPS 2024