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

Theory

1,082 papers

Papers per year

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

Papers

Phase diagram of early training dynamics in deep neural networks: effect of the learning rate, depth, and width NIPS 2023
On the Stability and Generalization of Triplet Learning AAAI 2023
Local Intrinsic Dimensional Entropy AAAI 2023
Neural Representations Reveal Distinct Modes of Class Fitting in Residual Convolutional Networks AAAI 2023
On the Expressive Flexibility of Self-Attention Matrices AAAI 2023
An Operator Theoretic Approach for Analyzing Sequence Neural Networks AAAI 2023
Experimental Observations of the Topology of Convolutional Neural Network Activations AAAI 2023
Fast Convergence in Learning Two-Layer Neural Networks with Separable Data AAAI 2023
Machines of Finite Depth: Towards a Formalization of Neural Networks AAAI 2023
The Implicit Regularization of Momentum Gradient Descent in Overparametrized Models AAAI 2023
The Analysis of Deep Neural Networks by Information Theory: From Explainability to Generalization AAAI 2023
Tokenization and the Noiseless Channel ACL 2023
Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions ACL 2023
Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings ACL 2023
Randomized Positional Encodings Boost Length Generalization of Transformers ACL 2023
Transformer Language Models Handle Word Frequency in Prediction Head ACL 2023
Honey, I Shrunk the Language: Language Model Behavior at Reduced Scale. ACL 2023
Uncovering Hidden Consequences of Pre-training Objectives in Sequence-to-Sequence Models ACL 2023
Beyond Positive Scaling: How Negation Impacts Scaling Trends of Language Models ACL 2023
Sequential Integrated Gradients: a simple but effective method for explaining language models ACL 2023
On the Expressivity Role of LayerNorm in Transformers’ Attention ACL 2023
Analysis of Catastrophic Forgetting for Random Orthogonal Transformation Tasks in the Overparameterized Regime AISTATS 2023
On double-descent in uncertainty quantification in overparametrized models AISTATS 2023
On the Accelerated Noise-Tolerant Power Method AISTATS 2023
Overparameterized Random Feature Regression with Nearly Orthogonal Data AISTATS 2023