NIPS Proceedingsβ

Cho-Jui Hsieh

20 Papers

  • A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks (2019)
  • A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning (2019)
  • Convergence of Adversarial Training in Overparametrized Neural Networks (2019)
  • Robustness Verification of Tree-based Models (2019)
  • Stochastic Shared Embeddings: Data-driven Regularization of Embedding Layers (2019)
  • Efficient Neural Network Robustness Certification with General Activation Functions (2018)
  • GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model Shrinking (2018)
  • Learning from Group Comparisons: Exploiting Higher Order Interactions (2018)
  • A Greedy Approach for Budgeted Maximum Inner Product Search (2017)
  • Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent (2017)
  • Scalable Demand-Aware Recommendation (2017)
  • A Comprehensive Linear Speedup Analysis for Asynchronous Stochastic Parallel Optimization from Zeroth-Order to First-Order (2016)
  • Asynchronous Parallel Greedy Coordinate Descent (2016)
  • Matrix Completion with Noisy Side Information (2015)
  • Sparse Linear Programming via Primal and Dual Augmented Coordinate Descent (2015)
  • Constant Nullspace Strong Convexity and Fast Convergence of Proximal Methods under High-Dimensional Settings (2014)
  • Fast Prediction for Large-Scale Kernel Machines (2014)
  • QUIC & DIRTY: A Quadratic Approximation Approach for Dirty Statistical Models (2014)
  • BIG & QUIC: Sparse Inverse Covariance Estimation for a Million Variables (2013)
  • Large Scale Distributed Sparse Precision Estimation (2013)