:: Library Catalog

Slika na naslovnici

Shranjeno v:

Bibliografske podrobnosti
Main Authors:	Li, Hongkang, Wang, Meng, Lu, Songtao, Cui, Xiaodong, Chen, Pin-Yu
Format:	Preprint
Izdano:	2024
Teme:	Machine Learning
Online dostop:	https://arxiv.org/abs/2402.15607
Oznake:	Označite Brez oznak, prvi označite!

Podobne knjige/članki

Can Mamba Learn In Context with Outliers? A Theoretical Generalization Analysis
od: Li, Hongkang, et al.
Izdano: (2025)

Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis
od: Li, Hongkang, et al.
Izdano: (2024)

When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers
od: Li, Hongkang, et al.
Izdano: (2025)

Learning on Transformers is Provable Low-Rank and Sparse: A One-layer Analysis
od: Li, Hongkang, et al.
Izdano: (2024)

What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding
od: Li, Hongkang, et al.
Izdano: (2024)

How does promoting the minority fraction affect generalization? A theoretical study of the one-hidden-layer neural network on group imbalance
od: Li, Hongkang, et al.
Izdano: (2024)

A Framework for Quantifying How Pre-Training and Context Benefit In-Context Learning
od: Song, Bingqing, et al.
Izdano: (2025)

Theoretical Learning Performance of Graph Neural Networks: The Impact of Jumping Connections and Layer-wise Sparsification
od: Sun, Jiawei, et al.
Izdano: (2025)

Transformers Learn the Optimal DDPM Denoiser for Multi-Token GMMs
od: Li, Hongkang, et al.
Izdano: (2026)

SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning
od: Zhang, Shuai, et al.
Izdano: (2024)

Understanding the Generalization of In-Context Learning in Transformers: An Empirical Study
od: Zhang, Xingxuan, et al.
Izdano: (2025)

Provable In-Context Learning of Nonlinear Regression with Transformers
od: Li, Hongbo, et al.
Izdano: (2025)

Optimality and NP-Hardness of Transformers in Learning Markovian Dynamical Functions
od: Ding, Yanna, et al.
Izdano: (2025)

Visual prompting reimagined: The power of the Activation Prompts
od: Zhang, Yihua, et al.
Izdano: (2026)

A Theoretical Analysis of Mamba's Training Dynamics: Filtering Relevant Features for Generalization in State Space Models
od: Shandirasegaran, Mugunthan, et al.
Izdano: (2026)

How do Transformers perform In-Context Autoregressive Learning?
od: Sander, Michael E., et al.
Izdano: (2024)

Understanding Generalization and Forgetting in In-Context Continual Learning
od: Li, Guangyu, et al.
Izdano: (2026)

Joint Unsupervised and Supervised Training for Automatic Speech Recognition via Bilevel Optimization
od: Saif, A F M, et al.
Izdano: (2024)

On the Role of Transformer Feed-Forward Layers in Nonlinear In-Context Learning
od: Sun, Haoyuan, et al.
Izdano: (2025)

Understanding In-Context Learning for Nonlinear Regression with Transformers: Attention as Featurizer
od: Hsu, Alexander, et al.
Izdano: (2026)

Do pretrained Transformers Learn In-Context by Gradient Descent?
od: Shen, Lingfeng, et al.
Izdano: (2023)

How Transformers Learn In-Context Recall Tasks? Optimality, Training Dynamics and Generalization
od: Nguyen, Quan, et al.
Izdano: (2025)

In-Context Compositional Learning via Sparse Coding Transformer
od: Chen, Wei, et al.
Izdano: (2025)

Objective Soups: Multilingual Multi-Task Modeling for Speech Processing
od: Saif, A F M, et al.
Izdano: (2025)

Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction Recognition
od: Liu, Mengyuan, et al.
Izdano: (2024)

Transformers Meet In-Context Learning: A Universal Approximation Theory
od: Li, Gen, et al.
Izdano: (2025)

Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape
od: Kim, Juno, et al.
Izdano: (2024)

Generative Pre-Trained Transformer for Symbolic Regression Base In-Context Reinforcement Learning
od: Li, Yanjie, et al.
Izdano: (2024)

Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning
od: Luo, Yuankai, et al.
Izdano: (2024)

Computational Safety for Generative AI: A Signal Processing Perspective
od: Chen, Pin-Yu
Izdano: (2025)

Meta-Learning Transformers to Improve In-Context Generalization
od: Braccaioli, Lorenzo, et al.
Izdano: (2025)

How Data Mixing Shapes In-Context Learning: Asymptotic Equivalence for Transformers with MLPs
od: Demir, Samet, et al.
Izdano: (2025)

How Do Transformers Learn Variable Binding in Symbolic Programs?
od: Wu, Yiwei, et al.
Izdano: (2025)

Improving Transformers using Faithful Positional Encoding
od: Idé, Tsuyoshi, et al.
Izdano: (2024)

In-Context In-Context Learning with Transformer Neural Processes
od: Ashman, Matthew, et al.
Izdano: (2024)

In-Context Learning with Representations: Contextual Generalization of Trained Transformers
od: Yang, Tong, et al.
Izdano: (2024)

Benchmarking General-Purpose In-Context Learning
od: Wang, Fan, et al.
Izdano: (2024)

How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic Interpretability
od: Im, Shawn, et al.
Izdano: (2026)

How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression
od: Chen, Xingwu, et al.
Izdano: (2024)

General-Purpose In-Context Learning by Meta-Learning Transformers
od: Kirsch, Louis, et al.
Izdano: (2022)