conftrace_
← Optimization & Theory
Deep Learning › Optimization & Theory ›

Theory

1,082 papers

Papers per year

4
2
97
81
'10
'15
'20
'25

Papers

Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training JMLR 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
On the Effectiveness of Iterative Learning Control L4DC 2022
ExSum: From Local Explanations to Model Understanding NAACL 2022
Overparameterization Improves Robustness to Covariate Shift in High Dimensions NIPS 2021
Rethinking the Variational Interpretation of Accelerated Optimization Methods NIPS 2021
A Central Limit Theorem for Differentially Private Query Answering NIPS 2021
Embedding Principle of Loss Landscape of Deep Neural Networks NIPS 2021
Parametric Complexity Bounds for Approximating PDEs with Neural Networks NIPS 2021
Analytic Study of Families of Spurious Minima in Two-Layer ReLU Neural Networks: A Tale of Symmetry II NIPS 2021
A Theoretical Analysis of Fine-tuning with Linear Teachers NIPS 2021
Linear Convergence of Gradient Methods for Estimating Structured Transition Matrices in High-dimensional Vector Autoregressive Models NIPS 2021
On Linear Stability of SGD and Input-Smoothness of Neural Networks NIPS 2021
Topological Detection of Trojaned Neural Networks NIPS 2021
The Implicit Bias of Minima Stability: A View from Function Space NIPS 2021
On the Frequency Bias of Generative Models NIPS 2021
Training Neural Networks is ER-complete NIPS 2021
Relative Flatness and Generalization NIPS 2021
On the Sample Complexity of Learning under Geometric Stability NIPS 2021
Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms NIPS 2021
Separation Results between Fixed-Kernel and Feature-Learning Probability Metrics NIPS 2021
Fast Axiomatic Attribution for Neural Networks NIPS 2021
Formalizing Generalization and Adversarial Robustness of Neural Networks to Weight Perturbations NIPS 2021