Tom Goldstein
Lawrence Livermore National Laboratory · 352 works · 14,044 citations · h-index 47
Top works
- The Split Bregman Method for L1-Regularized Problems
- Visualizing the Loss Landscape of Neural Nets
- Fast Alternating Direction Optimization Methods
- Geometric Applications of the Split Bregman Method: Segmentation and Surface Reconstruction
- Quantized Precoding for Massive MU-MIMO
- Channel Charting: Locating Users Within the Radio Environment Using Channel State Information
- Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
- Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses
- A Watermark for Large Language Models
- DCAN: Dual Channel-Wise Alignment Networks for Unsupervised Scene Adaptation
- FreeLB: Enhanced Adversarial Training for Natural Language Understanding
- A Field Guide to Forward-Backward Splitting with a FASTA Implementation
- Training Quantized Nets: A Deeper Understanding
- Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models
- Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors
- Decentralized Baseband Processing for Massive MU-MIMO Systems
- PhaseMax: Convex Phase Retrieval via Basis Pursuit
- Universal Guidance for Diffusion Models
- Training Neural Networks Without Gradients: A Scalable ADMM Approach
- Transferable Clean-Label Poisoning Attacks on Deep Neural Nets