conftrace_

theoretical analysis

97 papers

Explore in graph

Co-occurring keywords

neural network (6616) learning theory (519) neural network optimization (1293) generative model (2892) attention mechanism (4001) representation learning (6206) language model (4599) transformer architecture (1560) gradient descent (1144) recurrent neural network (1790)

Papers

Theoretical Analysis of Hierarchical Language Recognition and Generation by Transformers without Positional Encoding ACL 2025
Fundamental Limits of Membership Inference Attacks on Machine Learning Models JMLR 2025
Scaling Capability in Token Space: An Analysis of Large Vision Language Model JMLR 2025
Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective ICCV 2025
On the Generalization of Feature Incremental Learning IJCAI 2025
An Augmentation Overlap Theory of Contrastive Learning JMLR 2025
Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling NIPS 2024
An exactly solvable model for emergence and scaling laws in the multitask sparse parity problem NIPS 2024
Model Collapse Demystified: The Case of Regression NIPS 2024
Quality-Diversity Algorithms Can Provably Be Helpful for Optimization IJCAI 2024
Provable and Efficient Dataset Distillation for Kernel Ridge Regression NIPS 2024
Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers NIPS 2024
What does guidance do? A fine-grained analysis in a simple setting NIPS 2024
Approximation Rate of the Transformer Architecture for Sequence Modeling NIPS 2024
Improved Sample Complexity Bounds for Diffusion Model Training NIPS 2024
On the Effect of Key Factors in Spurious Correlation: A theoretical Perspective AISTATS 2024
From Activation to Initialization: Scaling Insights for Optimizing Neural Fields CVPR 2024
Learnability of high-dimensional targets by two-parameter models and gradient flow NIPS 2024
Understanding Transformer Reasoning Capabilities via Graph Algorithms NIPS 2024
Bridging the Divide: Reconsidering Softmax and Linear Attention NIPS 2024
On the Representational Capacity of Neural Language Models with Chain-of-Thought Reasoning ACL 2024
On the Ability of Developers' Training Data Preservation of Learnware NIPS 2024
Language Generation in the Limit NIPS 2024
Can Transformers Learn n-gram Language Models? EMNLP 2024
A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention NIPS 2024