Theory

Spurious Valleys and Clustering Behavior of Neural Networks ICML 2023 Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks NeurIPS 2023 Stochastic Gradient Descent-Induced Drift of Representation in a Two-Layer Neural Network ICML 2023 Synthetic data for model selection ICML 2023 The Analysis of Deep Neural Networks by Information Theory: From Explainability to Generalization AAAI 2023 The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks NeurIPS 2023 The Expressive Power of Tuning Only the Normalization Layers COLT 2023 The Hessian perspective into the Nature of Convolutional Neural Networks ICML 2023 The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural Networks COLT 2023 The Implicit Regularization of Dynamical Stability in Stochastic Gradient Descent ICML 2023 The Implicit Regularization of Momentum Gradient Descent in Overparametrized Models AAAI 2023 The NLP Task Effectiveness of Long-Range Transformers EACL 2023 Theoretical and Practical Perspectives on what Influence Functions Do NeurIPS 2023 Tokenization and the Noiseless Channel ACL 2023 Top-Ambiguity Samples Matter: Understanding Why Deep Ensemble Works in Selective Classification NeurIPS 2023 Towards Constituting Mathematical Structures for Learning to Optimize ICML 2023 Towards the Difficulty for a Deep Neural Network to Learn Concepts of Different Complexities NeurIPS 2023 Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete NeurIPS 2023 Training Neural Networks is NP-Hard in Fixed Dimension NeurIPS 2023 Transformer Language Models Handle Word Frequency in Prediction Head ACL 2023 Transformers learn through gradual rank increase NeurIPS 2023 Tuning Frequency Bias in Neural Network Training with Nonuniform Data ICLR 2023 Uncovering Hidden Consequences of Pre-training Objectives in Sequence-to-Sequence Models ACL 2023 Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias ICML 2023 Understanding Imbalanced Semantic Segmentation Through Neural Collapse CVPR 2023