conftrace_
← Deep Learning
Deep Learning ›

Optimization & Theory

6,829 papers (27 classified directly here)

Subtopics

Model Compression (1,785) Optimization (1,664) Efficient Computing (1,579) Theory (1,082) Neural Network Optimization (903) Evaluation (509) Loss Functions (123) Interpretability (105) Stochastic Methods (97) Regularization (77) Generalization (24) Sparse Optimization (7)

Papers per year

8
50
642
1173
'10
'15
'20
'25

Papers (including subtopics)

Proximal and Federated Random Reshuffling ICML 2022
ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally! ICML 2022
Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions ICML 2022
Power-Law Escape Rate of SGD ICML 2022
Bounding the Width of Neural Networks via Coupled Initialization A Worst Case Analysis ICML 2022
PAC-Net: A Model Pruning Approach to Inductive Transfer Learning ICML 2022
AutoSNN: Towards Energy-Efficient Spiking Neural Networks ICML 2022
Implicit Bias of the Step Size in Linear Diagonal Neural Networks ICML 2022
Overcoming Oscillations in Quantization-Aware Training ICML 2022
Measuring Representational Robustness of Neural Networks Through Shared Invariances ICML 2022
Fast Finite Width Neural Tangent Kernel ICML 2022
A Study on the Ramanujan Graph Property of Winning Lottery Tickets ICML 2022
A Unified Weight Initialization Paradigm for Tensorial Convolutional Neural Networks ICML 2022
POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging ICML 2022
A Differential Entropy Estimator for Training Neural Networks ICML 2022
Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry ICML 2022
Adaptive Second Order Coresets for Data-efficient Machine Learning ICML 2022
A Simple Guard for Learned Optimizers ICML 2022
Universal Joint Approximation of Manifolds and Densities by Simple Injective Flows ICML 2022
Large-scale Stochastic Optimization of NDCG Surrogates for Deep Learning with Provable Convergence ICML 2022
Winning the Lottery Ahead of Time: Efficient Early Network Pruning ICML 2022
DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale ICML 2022
Universality of Winning Tickets: A Renormalization Group Perspective ICML 2022
Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs ICML 2022
3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation ICML 2022