Picture for Hossein Taheri

Hossein Taheri

On the Optimization and Generalization of Multi-head Attention

Oct 19, 2023
Viaarxiv icon

Fast Convergence in Learning Two-Layer Neural Networks with Separable Data

May 22, 2023
Figure 1 for Fast Convergence in Learning Two-Layer Neural Networks with Separable Data
Figure 2 for Fast Convergence in Learning Two-Layer Neural Networks with Separable Data
Figure 3 for Fast Convergence in Learning Two-Layer Neural Networks with Separable Data
Viaarxiv icon

Generalization and Stability of Interpolating Neural Networks with Minimal Width

Feb 18, 2023
Viaarxiv icon

Decentralized Learning with Separable Data: Generalization and Fast Algorithms

Sep 16, 2022
Figure 1 for Decentralized Learning with Separable Data: Generalization and Fast Algorithms
Figure 2 for Decentralized Learning with Separable Data: Generalization and Fast Algorithms
Figure 3 for Decentralized Learning with Separable Data: Generalization and Fast Algorithms
Figure 4 for Decentralized Learning with Separable Data: Generalization and Fast Algorithms
Viaarxiv icon

Asymptotic Behavior of Adversarial Training in Binary Classification

Oct 26, 2020
Figure 1 for Asymptotic Behavior of Adversarial Training in Binary Classification
Figure 2 for Asymptotic Behavior of Adversarial Training in Binary Classification
Viaarxiv icon

Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions

Jul 05, 2020
Figure 1 for Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions
Figure 2 for Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions
Figure 3 for Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions
Figure 4 for Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions
Viaarxiv icon

Sharp Asymptotics and Optimal Performance for Inference in Binary Models

Feb 26, 2020
Figure 1 for Sharp Asymptotics and Optimal Performance for Inference in Binary Models
Figure 2 for Sharp Asymptotics and Optimal Performance for Inference in Binary Models
Figure 3 for Sharp Asymptotics and Optimal Performance for Inference in Binary Models
Figure 4 for Sharp Asymptotics and Optimal Performance for Inference in Binary Models
Viaarxiv icon

Quantized Push-sum for Gossip and Decentralized Optimization over Directed Graphs

Feb 25, 2020
Figure 1 for Quantized Push-sum for Gossip and Decentralized Optimization over Directed Graphs
Figure 2 for Quantized Push-sum for Gossip and Decentralized Optimization over Directed Graphs
Figure 3 for Quantized Push-sum for Gossip and Decentralized Optimization over Directed Graphs
Figure 4 for Quantized Push-sum for Gossip and Decentralized Optimization over Directed Graphs
Viaarxiv icon

Sharp Guarantees for Solving Random Equations with One-Bit Information

Aug 12, 2019
Figure 1 for Sharp Guarantees for Solving Random Equations with One-Bit Information
Figure 2 for Sharp Guarantees for Solving Random Equations with One-Bit Information
Figure 3 for Sharp Guarantees for Solving Random Equations with One-Bit Information
Figure 4 for Sharp Guarantees for Solving Random Equations with One-Bit Information
Viaarxiv icon

Robust and Communication-Efficient Collaborative Learning

Add code
Jul 24, 2019
Figure 1 for Robust and Communication-Efficient Collaborative Learning
Figure 2 for Robust and Communication-Efficient Collaborative Learning
Figure 3 for Robust and Communication-Efficient Collaborative Learning
Viaarxiv icon