gradient ascent

Unlearning Traces the Influential Training Data of Language Models ACL 2024 Adversarial Robustness via Random Projection Filters CVPR 2023 Bit Allocation using Optimization ICML 2023 Gradient Ascent Post-training Enhances Language Model Generalization ACL 2023 Knowledge Unlearning for Mitigating Privacy Risks in Language Models ACL 2023 Parallel-mentoring for Offline Model-based Optimization NeurIPS 2023 Performative Reinforcement Learning ICML 2023 Simulated Annealing in Early Layers Leads to Better Generalization CVPR 2023 Adversarial Robustness is at Odds with Lazy Training NeurIPS 2022 Augmented Sliced Wasserstein Distances ICLR 2022 Minimax Optimization with Smooth Algorithmic Adversaries ICLR 2022 Mode estimation on matrix manifolds: Convergence and robustness AISTATS 2022 Stochastic Continuous Submodular Maximization: Boosting via Non-oblivious Function ICML 2022 A Novel Method to Solve Neural Knapsack Problems ICML 2021 Anti-Backdoor Learning: Training Clean Models on Poisoned Data NeurIPS 2021 Learning in Markets: Greed Leads to Chaos but Following the Price is Right IJCAI 2021 Leveraging Non-uniformity in First-order Non-convex Optimization ICML 2021 Score-Based Point Cloud Denoising ICCV 2021 Synthesize-It-Classifier: Learning a Generative Classifier Through Recurrent Self-Analysis CVPR 2021 Best Arm Identification in Spectral Bandits IJCAI 2020 Cooperative Multi-player Bandit Optimization NeurIPS 2020 SIGUA: Forgetting May Make Learning with Noisy Labels More Robust ICML 2020 Curls & Whey: Boosting Black-Box Adversarial Attacks CVPR 2019 Model-Free IRL Using Maximum Likelihood Estimation AAAI 2019 From Stochastic Planning to Marginal MAP NeurIPS 2018