Picture for Amin Karbasi

Amin Karbasi

EPFL

Injecting Undetectable Backdoors in Deep Learning and Language Models

Add code
Jun 09, 2024
Viaarxiv icon

On the Computational Landscape of Replicable Learning

Add code
May 24, 2024
Viaarxiv icon

Replicable Learning of Large-Margin Halfspaces

Add code
Feb 21, 2024
Viaarxiv icon

SubGen: Token Generation in Sublinear Time and Memory

Add code
Feb 08, 2024
Viaarxiv icon

Tree of Attacks: Jailbreaking Black-Box LLMs Automatically

Add code
Dec 04, 2023
Viaarxiv icon

Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization

Add code
Oct 26, 2023
Figure 1 for Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization
Figure 2 for Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization
Figure 3 for Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization
Figure 4 for Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization
Viaarxiv icon

HyperAttention: Long-context Attention in Near-Linear Time

Add code
Oct 11, 2023
Figure 1 for HyperAttention: Long-context Attention in Near-Linear Time
Figure 2 for HyperAttention: Long-context Attention in Near-Linear Time
Figure 3 for HyperAttention: Long-context Attention in Near-Linear Time
Figure 4 for HyperAttention: Long-context Attention in Near-Linear Time
Viaarxiv icon

Optimal Learners for Realizable Regression: PAC Learning and Online Learning

Add code
Jul 07, 2023
Figure 1 for Optimal Learners for Realizable Regression: PAC Learning and Online Learning
Viaarxiv icon

Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning

Add code
Jun 15, 2023
Figure 1 for Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning
Figure 2 for Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning
Figure 3 for Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning
Figure 4 for Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning
Viaarxiv icon

Replicability in Reinforcement Learning

Add code
May 31, 2023
Figure 1 for Replicability in Reinforcement Learning
Figure 2 for Replicability in Reinforcement Learning
Figure 3 for Replicability in Reinforcement Learning
Viaarxiv icon