Krishnamurthy Dvijotham

papers

619

total citations

papers (14)

Stealing part of a production language model

ICML 2024arXiv

145

citations

Rich Human Feedback for Text-to-Image Generation

CVPR 2024arXiv

134

citations

Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming

NEURIPS 2020arXiv

101

citations

The Autoencoding Variational Autoencoder

NEURIPS 2020arXiv

citations

Achieving Robustness in the Wild via Adversarial Mixing With Disentangled Representations

CVPR 2020arXiv

citations

Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation

ICML 2024arXiv

citations

Efficient Error Certification for Physics-Informed Neural Networks

ICML 2024arXiv

citations

Overcoming the Convex Barrier for Simplex Inputs

NEURIPS 2021

citations

Training Private Models That Know What They Don’t Know

NEURIPS 2023

citations

Monotone, Bi-Lipschitz, and Polyak-Łojasiewicz Networks

ICML 2024

citations

Krishnamurthy Dvijotham

papers (14)

Stealing part of a production language model

Rich Human Feedback for Text-to-Image Generation

Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming

The Autoencoding Variational Autoencoder

Achieving Robustness in the Wild via Adversarial Mixing With Disentangled Representations

Learning to Receive Help: Intervention-Aware Concept Embedding Models

Provably Bounding Neural Network Preimages

Make Sure You're Unsure: A Framework for Verifying Probabilistic Specifications

An efficient nonconvex reformulation of stagewise convex optimization problems

Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation

Efficient Error Certification for Physics-Informed Neural Networks

Overcoming the Convex Barrier for Simplex Inputs

Training Private Models That Know What They Don’t Know

Monotone, Bi-Lipschitz, and Polyak-Łojasiewicz Networks

papers (14)

Stealing part of a production language model

Rich Human Feedback for Text-to-Image Generation

Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming

The Autoencoding Variational Autoencoder

Achieving Robustness in the Wild via Adversarial Mixing With Disentangled Representations

Learning to Receive Help: Intervention-Aware Concept Embedding Models

Provably Bounding Neural Network Preimages

Make Sure You're Unsure: A Framework for Verifying Probabilistic Specifications

An efficient nonconvex reformulation of stagewise convex optimization problems

Private Gradient Descent for Linear Regression: Tighter Error Bounds and Instance-Specific Uncertainty Estimation

Efficient Error Certification for Physics-Informed Neural Networks

Overcoming the Convex Barrier for Simplex Inputs

Training Private Models That Know What They Don’t Know

Monotone, Bi-Lipschitz, and Polyak-Łojasiewicz Networks