Amin Karbasi

Adversarial Reasoning at Jailbreaking Time ICML 2025 Intelligence at the Edge of Chaos ICLR 2025 Large Language Models Encode Semantics and Alignment in Linearly Separable Representations IJCNLP 2025 Learning Task Representations from In-Context Learning ACL 2025 Procurement Auctions via Approximately Optimal Submodular Optimization ICML 2025 Cell2Sentence: Teaching Large Language Models the Language of Biology ICML 2024 HyperAttention: Long-context Attention in Near-Linear Time ICLR 2024 Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models NeurIPS 2024 On the Computational Landscape of Replicable Learning NeurIPS 2024 Repeated Random Sampling for Minimizing the Time-to-Accuracy of Learning ICLR 2024 Replicable Learning of Large-Margin Halfspaces ICML 2024 Submodular Minimax Optimization: Finding Effective Sets AISTATS 2024 The Impossibility of Parallelizing Boosting ALT 2024 Tree of Attacks: Jailbreaking Black-Box LLMs Automatically NeurIPS 2024 TSDS: Data Selection for Task-Specific Model Finetuning NeurIPS 2024 Universal Rates for Active Learning NeurIPS 2024 Universal Rates for Regression: Separations between Cut-Off and Absolute Loss COLT 2024 Beyond Lipschitz: Sharp Generalization and Excess Risk Bounds for Full-Batch GD ICLR 2023 Exact Gradient Computation for Spiking Neural Networks via Forward Propagation AISTATS 2023 How Do You Want Your Greedy: Simultaneous or Repeated? JMLR 2023 KDEformer: Accelerating Transformers via Kernel Density Estimation ICML 2023 Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning ICML 2023 Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization NeurIPS 2023 Optimal Learners for Realizable Regression: PAC Learning and Online Learning NeurIPS 2023 Replicability in Reinforcement Learning NeurIPS 2023 Replicable Bandits ICLR 2023 Replicable Clustering NeurIPS 2023 Statistical Indistinguishability of Learning Algorithms ICML 2023 Black-Box Generalization: Stability of Zeroth-Order Learning NeurIPS 2022 Fast Neural Kernel Embeddings for General Activations NeurIPS 2022 Federated Functional Gradient Boosting AISTATS 2022 Learning Distributionally Robust Models at Scale via Composite Optimization ICLR 2022 Multiclass Learnability Beyond the PAC Framework: Universal Rates and Partial Concept Classes NeurIPS 2022 On Optimal Learning Under Targeted Data Poisoning NeurIPS 2022 Reinforcement Learning with Logarithmic Regret and Policy Switches NeurIPS 2022 Scalable MCMC Sampling for Nonsymmetric Determinantal Point Processes ICML 2022 Scalable Sampling for Nonsymmetric Determinantal Point Processes ICLR 2022 Self-Consistency of the Fokker Planck Equation COLT 2022 Submodular Maximization in Clean Linear Time NeurIPS 2022 Universal Rates for Interactive Learning NeurIPS 2022 Adaptivity in Adaptive Submodularity COLT 2021 An Exponential Improvement on the Memorization Capacity of Deep Threshold Networks NeurIPS 2021 Learning and certification under instance-targeted poisoning UAI 2021 Meta Learning in the Continuous Time Limit AISTATS 2021 Multiple Descent: Design Your Own Generalization Curve NeurIPS 2021 Parallelizing Thompson Sampling NeurIPS 2021 Regret Bounds for Batched Bandits AAAI 2021 Regularized Submodular Maximization at Scale ICML 2021 Submodular + Concave NeurIPS 2021 The curious case of adversarially robust models: More data can help, double descend, or hurt generalization UAI 2021 Black Box Submodular Maximization: Discrete and Continuous Settings AISTATS 2020 Continuous Submodular Maximization: Beyond DR-Submodularity NeurIPS 2020 Minimax Regret of Switching-Constrained Online Convex Optimization: No Phase Transition NeurIPS 2020 More Data Can Expand The Generalization Gap Between Adversarially Robust and Standard Models ICML 2020 One Sample Stochastic Frank-Wolfe AISTATS 2020 Online MAP Inference of Determinantal Point Processes NeurIPS 2020 Quantized Frank-Wolfe: Faster Optimization, Lower Communication, and Projection Free AISTATS 2020 Stochastic Conditional Gradient Methods: From Convex Minimization to Submodular Maximization JMLR 2020 Streaming Submodular Maximization under a k-Set System Constraint ICML 2020 Submodular Maximization Through Barrier Functions NeurIPS 2020 Adaptive Sequence Submodularity NeurIPS 2019 Eliminating Latent Discrimination: Train Then Mask AAAI 2019 Online Continuous Submodular Maximization: From Full-Information to Bandit Feedback NeurIPS 2019 Projection-Free Bandit Convex Optimization AISTATS 2019 Stochastic Continuous Greedy ++: When Upper and Lower Bounds Match NeurIPS 2019 Submodular Maximization beyond Non-negativity: Guarantees, Fast Algorithms, and Applications ICML 2019 Submodular Streaming in All Its Glory: Tight Approximation, Minimum Memory and Low Adaptive Complexity ICML 2019 Comparison Based Learning from Weak Oracles AISTATS 2018 Conditional Gradient Method for Stochastic Submodular Maximization: Closing the Gap AISTATS 2018 Data Summarization at Scale: A Two-Stage Submodular Approach ICML 2018 Decentralized Submodular Maximization: Bridging Discrete and Continuous Settings ICML 2018 Do Less, Get More: Streaming Submodular Maximization with Subsampling NeurIPS 2018 Online Continuous Submodular Maximization AISTATS 2018 Projection-Free Online Optimization with Stochastic Gradient: From Convexity to Submodularity ICML 2018 Scalable Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints ICML 2018 Submodularity on Hypergraphs: From Sets to Sequences AISTATS 2018 Weakly Submodular Maximization Beyond Cardinality Constraints: Does Randomization Help Greedy? ICML 2018 Deletion-Robust Submodular Maximization: Data Summarization with “the Right to be Forgotten” ICML 2017 Differentially Private Submodular Maximization: Data Summarization in Disguise ICML 2017 Gradient Methods for Submodular Maximization NeurIPS 2017 Greed Is Good: Near-Optimal Submodular Maximization via Greedy Optimization COLT 2017 Interactive Submodular Bandit NeurIPS 2017 Probabilistic Submodular Maximization in Sub-Linear Time ICML 2017 Streaming Weak Submodularity: Interpreting Neural Networks on the Fly NeurIPS 2017 Distributed Submodular Maximization JMLR 2016 Estimating the Size of a Large Network and its Communities from a Random Sample NeurIPS 2016 Fast Constrained Submodular Maximization: Personalized Data Summarization ICML 2016 Fast Distributed Submodular Cover: Public-Private Data Summarization NeurIPS 2016 Distributed Submodular Cover: Succinctly Summarizing Massive Data NeurIPS 2015 Fast Mixing for Discrete Point Processes COLT 2015 Non-Monotone Adaptive Submodular Maximization IJCAI 2015 Sequential Information Maximization: When is Greedy Near-optimal? COLT 2015 Tradeoffs for Space, Time, Data and Risk in Unsupervised Learning AISTATS 2015 Near Optimal Bayesian Active Learning for Decision Making AISTATS 2014 Near-Optimally Teaching the Crowd to Classify ICML 2014 Distributed Submodular Maximization: Identifying Representative Elements in Massive Data NeurIPS 2013 Iterative Learning and Denoising in Convolutional Neural Associative Memories ICML 2013 Noise-Enhanced Associative Memories NeurIPS 2013