← Optimization & Theory
Deep Learning › Optimization & Theory ›

Theory

1072 directly classified papers

Papers per year

Papers

A Unified Convergence Theorem for Stochastic Optimization Methods NIPS 2022
Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent JMLR 2022
A proof of convergence for the gradient descent optimization method with random initializations in the training of neural networks with ReLU activation for piecewise linear target functions JMLR 2022
Intrinsic Dimension Estimation Using Wasserstein Distance JMLR 2022
Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximation CVPR 2022
Rank Diminishing in Deep Neural Networks NIPS 2022
In What Ways Are Deep Neural Networks Invariant and How Should We Measure This? NIPS 2022
Benefits of Additive Noise in Composing Classes with Bounded Capacity NIPS 2022
On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias NIPS 2022
Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks NIPS 2022
Differentially Private Learning with Margin Guarantees NIPS 2022
Language Model Decomposition: Quantifying the Dependency and Correlation of Language Models EMNLP 2022
Exploring Mode Connectivity for Pre-trained Language Models EMNLP 2022
The Architectural Bottleneck Principle EMNLP 2022
Outlier Dimensions that Disrupt Transformers are Driven by Frequency EMNLP 2022
Post-Hoc Interpretation of Transformer Hyperparameters with Explainable Boosting Machines EMNLP 2022
Are All Losses Created Equal: A Neural Collapse Perspective NIPS 2022
PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization NIPS 2022
From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent NIPS 2022
Analyzing Lottery Ticket Hypothesis from PAC-Bayesian Theory Perspective NIPS 2022
Effects of Data Geometry in Early Deep Learning NIPS 2022
Incremental Learning via Rate Reduction CVPR 2021
Provably Strict Generalisation Benefit for Equivariant Models ICML 2021
Revealing the Structure of Deep Neural Networks via Convex Duality ICML 2021
Separation Results between Fixed-Kernel and Feature-Learning Probability Metrics NIPS 2021