← Optimization & Theory
Deep Learning › Optimization & Theory ›

Optimization

1638 directly classified papers

Papers per year

Papers

Combining Slow and Fast: Complementary Filtering for Dynamics Learning AAAI 2023
Linear Regularizers Enforce the Strict Saddle Property AAAI 2023
Gold Doesn’t Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information EACL 2023
User-Controllable Arbitrary Style Transfer via Entropy Regularization AAAI 2023
TACCL: Guiding Collective Algorithm Synthesis using Communication Sketches NSDI 2023
Better Together: Jointly Optimizing ML Collective Scheduling and Execution Planning using SYNDICATE NSDI 2023
A Learnable Radial Basis Positional Embedding for Coordinate-MLPs AAAI 2023
LagNet: Deep Lagrangian Mechanics for Plug-and-Play Molecular Representation Learning AAAI 2023
AAAI New Faculty Highlights: General and Scalable Optimization for Robust AI AAAI 2023
GeoLS: Geodesic Label Smoothing for Image Segmentation MIDL 2023
spred: Solving L1 Penalty with SGD ICML 2023
Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs ICML 2023
Optimal Shrinkage for Distributed Second-Order Optimization ICML 2023
KDEformer: Accelerating Transformers via Kernel Density Estimation ICML 2023
Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks ICML 2023
Bit Allocation using Optimization ICML 2023
Improving Bi-level Optimization Based Methods with Inspiration from Humans’ Classroom Study Techniques ICML 2023
On the Training Instability of Shuffling SGD with Batch Normalization ICML 2023
Anchor Sampling for Federated Learning with Partial Client Participation ICML 2023
Decentralized SGD and Average-direction SAM are Asymptotically Equivalent ICML 2023
Two Losses Are Better Than One: Faster Optimization Using a Cheaper Proxy ICML 2023
Optimizing Mode Connectivity for Class Incremental Learning ICML 2023
Global optimality for Euclidean CCCP under Riemannian convexity ICML 2023
Robustly Learning a Single Neuron via Sharpness ICML 2023
CocktailSGD: Fine-tuning Foundation Models over 500Mbps Networks ICML 2023