Skip to content
conftrace_

Optimization & Theory

43,292 papers (3 classified directly here)

Subtopics · a paper can sit in several, so these overlap

Optimization (17,731) Learning Theory (6,809) Bayesian Inference (6,267) Theory (5,579) Statistical Learning (4,564) Neural Network Optimization (4,155) Stochastic Processes (2,948) Stochastic Methods (1,283) Loss Functions (1,220) Distributed Learning (1,202) Online Algorithms (1,013) Statistics (822) Generalization (376) Information Theory (370) Sample Complexity (282) Sparse Optimization (241) Game Theory (151) Convex Optimization (132) Optimal Transport (104) Robust Optimization (84) Distributed Optimization (73) Approximation Algorithms (33)

Papers per year

1
52
352
828
3,646
5,854
2000
'5
'10
'15
'20
'25

Papers (including subtopics)

When Are Solutions Connected in Deep Networks? NeurIPS 2021 When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute EMNLP 2021 When Does Gradient Descent with Logistic Loss Find Interpolating Two-Layer Networks? JMLR 2021 When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations? COLT 2021 When does preconditioning help or hurt generalization? ICLR 2021 When Do You Need Billions of Words of Pretraining Data? ACL 2021 When Expressivity Meets Trainability: Fewer than n Neurons Can Work NeurIPS 2021 When in Doubt: Improving Classification Performance with Alternating Normalization EMNLP 2021 When Is Generalizable Reinforcement Learning Tractable? NeurIPS 2021 When is particle filtering efficient for planning in partially observed linear dynamical systems? UAI 2021 When Is Unsupervised Disentanglement Possible? NeurIPS 2021 When Optimizing f-Divergence is Robust with Label Noise ICLR 2021 When OT meets MoM: Robust estimation of Wasserstein Distance AISTATS 2021 When random initializations help: a study of variational inference for community detection JMLR 2021 Which transformer architecture fits my data? A vocabulary bottleneck in self-attention ICML 2021 Whitening and Second Order Optimization Both Make Information in the Dataset Unusable During Training, and Can Reduce or Prevent Generalization ICML 2021 Why Adversarial Interaction Creates Non-Homogeneous Patterns: A Pseudo-Reaction-Diffusion Model for Turing Instability AAAI 2021 Why Approximate Matrix Square Root Outperforms Accurate SVD in Global Covariance Pooling? ICCV 2021 Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets? ICLR 2021 Why did the distribution change? AISTATS 2021 Why Do Better Loss Functions Lead to Less Transferable Features? NeurIPS 2021 Why Do Document-Level Polarity Classifiers Fail? NAACL 2021 Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability NeurIPS 2021 Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Sparse Neural Networks NeurIPS 2021 Why resampling outperforms reweighting for correcting sampling bias with stochastic gradients ICLR 2021