conftrace_

gradient ascent

51 papers

Explore in graph

Also known as

GA

Co-occurring keywords

machine unlearning (290) large language model (13587) privacy preservation (380) knowledge forgetting (34) knowledge distillation (3725) knowledge removal (20) adversarial example (564) multimodal large language model (966) generative model (2892) adversarial attack (1621)

Papers

Performative Reinforcement Learning ICML 2023
Gradient Ascent Post-training Enhances Language Model Generalization ACL 2023
Adversarial Robustness via Random Projection Filters CVPR 2023
Knowledge Unlearning for Mitigating Privacy Risks in Language Models ACL 2023
Simulated Annealing in Early Layers Leads to Better Generalization CVPR 2023
Stochastic Continuous Submodular Maximization: Boosting via Non-oblivious Function ICML 2022
Adversarial Robustness is at Odds with Lazy Training NIPS 2022
Mode estimation on matrix manifolds: Convergence and robustness AISTATS 2022
Score-Based Point Cloud Denoising ICCV 2021
Anti-Backdoor Learning: Training Clean Models on Poisoned Data NIPS 2021
Learning in Markets: Greed Leads to Chaos but Following the Price is Right IJCAI 2021
Synthesize-It-Classifier: Learning a Generative Classifier Through Recurrent Self-Analysis CVPR 2021
A Novel Method to Solve Neural Knapsack Problems ICML 2021
Leveraging Non-uniformity in First-order Non-convex Optimization ICML 2021
Best Arm Identification in Spectral Bandits IJCAI 2020
Cooperative Multi-player Bandit Optimization NIPS 2020
SIGUA: Forgetting May Make Learning with Noisy Labels More Robust ICML 2020
Model-Free IRL Using Maximum Likelihood Estimation AAAI 2019
Curls & Whey: Boosting Black-Box Adversarial Attacks CVPR 2019
Interpretable Textual Neuron Representations for NLP EMNLP 2018
From Stochastic Planning to Marginal MAP NIPS 2018
On the Optimization Landscape of Tensor Decompositions NIPS 2017
A Robust Noise Resistant Algorithm for POI Identification from Flickr Data IJCAI 2017
Deep Neural Networks Are Easily Fooled: High Confidence Predictions for Unrecognizable Images CVPR 2015
Attractor Network Dynamics Enable Preplay and Rapid Path Planning in Maze–like Environments NIPS 2015