← Optimization & Theory
Deep Learning › Optimization & Theory ›

Theory

1072 directly classified papers

Papers per year

Papers

Learnability of high-dimensional targets by two-parameter models and gradient flow NIPS 2024
Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature NIPS 2024
In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization NIPS 2024
Globally Convergent Variational Inference NIPS 2024
Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling NIPS 2024
Understanding Surprising Generalization Phenomena in Deep Learning AAAI 2024
What do Graph Neural Networks learn? Insights from Tropical Geometry NIPS 2024
Evaluating the design space of diffusion-based generative models NIPS 2024
The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof NIPS 2024
Your Transformer is Secretly Linear ACL 2024
Batch Normalization Is Blind to the First and Second Derivatives of the Loss AAAI 2024
Topological obstruction to the training of shallow ReLU neural networks NIPS 2024
Improved Sample Complexity Bounds for Diffusion Model Training NIPS 2024
The Expressive Capacity of State Space Models: A Formal Language Perspective NIPS 2024
Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning NIPS 2024
Model Collapse Demystified: The Case of Regression NIPS 2024
Unveiling Linguistic Regions in Large Language Models ACL 2024
AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters ACL 2024
Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models NIPS 2024
Understanding Generalizability of Diffusion Models Requires Rethinking the Hidden Gaussian Structure NIPS 2024
Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit NIPS 2024
Scaling Laws in Linear Regression: Compute, Parameters, and Data NIPS 2024
Optimization Can Learn Johnson Lindenstrauss Embeddings NIPS 2024
Neural Collapse To Multiple Centers For Imbalanced Data NIPS 2024
Exponential Hardness of Optimization from the Locality in Quantum Neural Networks AAAI 2024