Cho-Jui Hsieh

74

Papers

1,783

Total Citations

Papers (74)

Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent

NeurIPS 2017arXiv

A Comprehensive Linear Speedup Analysis for Asynchronous Stochastic Parallel Optimization from Zeroth-Order to First-Order

NeurIPS 2016arXiv

OR-Bench: An Over-Refusal Benchmark for Large Language Models

A Greedy Approach for Budgeted Maximum Inner Product Search

NeurIPS 2017arXiv

Two-stage LLM Fine-tuning with Less Specialization and More Generalization

Asynchronous Parallel Greedy Coordinate Descent

MetaDistiller: Network Self-Boosting via Meta-Learned Top-Down Distillation

Is Your Multimodal Language Model Oversensitive to Safe Queries?

LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization

Scalable Demand-Aware Recommendation

NeurIPS 2017arXiv

Sparse Linear Programming via Primal and Dual Augmented Coordinate Descent

Matrix Completion with Noisy Side Information

Expert Proximity as Surrogate Rewards for Single Demonstration Imitation Learning

One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts

Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation

On Discrete Prompt Optimization for Diffusion Models

Ameliorate Spurious Correlations in Dataset Condensation

Rob-GAN: Generator, Discriminator, and Adversarial Attacker

How Does Noise Help Robustness? Explanation and Exploration under the Neural SDE Framework

Robust and Accurate Object Detection via Adversarial Learning

Towards Efficient and Scalable Sharpness-Aware Minimization

FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning

Evaluating Robustness of Deep Image Super-Resolution Against Adversarial Attacks

RandomRooms: Unsupervised Pre-Training From Synthetic Shapes and Randomized Layouts for 3D Object Detection

Towards Robustness of Deep Neural Networks via Regularization

RANK-NOSH: Efficient Predictor-Based Architecture Search via Non-Uniform Successive Halving

Improved Adversarial Training via Learned Optimizer

Learning to Learn with Smooth Regularization

Random Sharpness-Aware Minimization

Efficient Non-Parametric Optimizer Search for Diverse Tasks

A Computationally Efficient Sparsified Online Newton Method

Robust Lipschitz Bandits to Adversarial Corruptions

Block Low-Rank Preconditioner with Shared Basis for Stochastic Optimization

Symbolic Discovery of Optimization Algorithms

Why Does Sharpness-Aware Minimization Generalize Better Than SGD?

Effective Robustness against Natural Distribution Shifts for Models with Different Training Data

Universality and Limitations of Prompt Tuning

PASSCoDe: Parallel ASynchronous Stochastic dual Co-ordinate Descent

PU Learning for Matrix Completion

Robust Principal Component Analysis with Side Information

Computationally Efficient Nyström Approximation using Fast Transforms

Gradient Boosted Decision Trees for High Dimensional Sparse Output

Extreme Learning to Rank via Low Rank Assumption

Fast Variance Reduction Method with Stochastic Batch Size

Towards Fast Computation of Certified Robustness for ReLU Networks

SQL-Rank: A Listwise Approach to Collaborative Ranking

Robust Decision Trees Against Adversarial Examples

Learning from Group Comparisons: Exploiting Higher Order Interactions

GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model Shrinking

Efficient Neural Network Robustness Certification with General Activation Functions

A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks

Convergence of Adversarial Training in Overparametrized Neural Networks

Stochastic Shared Embeddings: Data-driven Regularization of Embedding Layers

A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning

Robustness Verification of Tree-based Models

Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond

Multi-Stage Influence Function

An Efficient Adversarial Attack for Tree Ensembles

Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data

Provably Robust Metric Learning

Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations

DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification

NeurIPS 2021arXiv

Label Disentanglement in Partition-based Extreme Multilabel Classification

Learnable Fourier Features for Multi-dimensional Spatial Positional Encoding

Fast Certified Robust Training with Short Warmup

DRONE: Data-aware Low-rank Compression for Large NLP Models

Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Robustness Verification

DC-BENCH: Dataset Condensation Benchmark

Syndicated Bandits: A Framework for Auto Tuning Hyper-parameters in Contextual Bandit Algorithms

General Cutting Planes for Bound-Propagation-Based Neural Network Verification

Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation

Are AlphaZero-like Agents Robust to Adversarial Perturbations?

ELIAS: End-to-End Learning to Index and Search in Large Output Spaces

Efficient Frameworks for Generalized Low-Rank Matrix Bandit Problems