Volkan Cevher

BLUR: A Bi-Level Optimization Approach for LLM Unlearning EACL 2026 SemEval-2025 Task 4: Unlearning sensitive content from Large Language Models SEMEVAL 2025 Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate NAACL 2025 Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning ICML 2025 IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic ICML 2025 Accelerating Spectral Clustering under Fairness Constraints ICML 2025 Training Deep Learning Models with Norm-Constrained LMOs ICML 2025 Layer-wise Quantization for Quantized Optimistic Dual Averaging ICML 2025 Best of Both Worlds: Regret Minimization versus Minimax Play ICML 2025 Continuous-Time Analysis of Heavy Ball Momentum in Min-Max Games ICML 2025 Generalization of noisy SGD in unbounded non-convex settings ICML 2025 Adversarial Training for Defense Against Label Poisoning Attacks ICLR 2025 Certified Robustness Under Bounded Levenshtein Distance ICLR 2025 Faster Inference of Flow-Based Generative Models via Improved Data-Noise Coupling ICLR 2025 Efficient Interpolation between Extragradient and Proximal Methods for Weak MVIs ICLR 2025 Addressing Label Shift in Distributed Learning via Entropy Regularization​ ICLR 2025 How Gradient descent balances features: A dynamical analysis for two-layer neural networks ICLR 2025 Quantum-PEFT: Ultra parameter-efficient fine-tuning ICLR 2025 LUME: LLM Unlearning with Multitask Evaluations EMNLP 2025 SemEval-2025 Task 4: Unlearning sensitive content from Large Language Models ACL 2025 Not Every Token Needs Forgetting: Selective Unlearning Balancing Forgetting and Utility in Large Language Models EMNLP 2025 Universal Gradient Methods for Stochastic Convex Optimization ICML 2024 $\boldsymbol{\mu}\mathbf{P^2}$: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling NIPS 2024 SAMPa: Sharpness-aware Minimization Parallelized NIPS 2024 On Feature Learning in Structured State Space Models NIPS 2024 Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces NIPS 2024 Membership Inference Attacks against Large Vision-Language Models NIPS 2024 Extreme Miscalibration and the Illusion of Adversarial Robustness ACL 2024 Krylov Cubic Regularized Newton: A Subspace Second-Order Method with Dimension-Free Convergence Rate AISTATS 2024 Efficient Continual Finite-Sum Minimization ICLR 2024 Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to Inexactness ICLR 2024 Multilinear Operator Networks ICLR 2024 Generalization of Scaled Deep ResNets in the Mean-Field Regime ICLR 2024 Robust NAS under adversarial training: benchmark, theory, and beyond ICLR 2024 Adversarial Training Should Be Cast as a Non-Zero-Sum Game ICLR 2024 Efficient local linearity regularization to overcome catastrophic overfitting ICLR 2024 Revisiting Character-level Adversarial Attacks for Language Models ICML 2024 REST: Efficient and Accelerated EEG Seizure Analysis through Residual State Updates ICML 2024 High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization ICML 2024 Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations ICML 2024 Truly No-Regret Learning in Constrained MDPs ICML 2024 MADA: Meta-Adaptive Optimizers Through Hyper-Gradient Descent ICML 2024 Learning to Remove Cuts in Integer Linear Programming ICML 2024 Imitation Learning in Discounted Linear MDPs without exploration assumptions ICML 2024 Improving SAM Requires Rethinking its Optimization Formulation ICML 2024 On the Generalization of Stochastic Gradient Descent with Momentum JMLR 2024 Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks JMLR 2024 Benign Overfitting in Deep Neural Networks under Lazy Training ICML 2023 Stable Nonconvex-Nonconcave Training via Linear Interpolation NIPS 2023 On the Convergence of Encoder-only Shallow Transformers NIPS 2023 Distributed Extra-gradient with Optimal Complexity and Communication Guarantees ICLR 2023 Solving stochastic weak Minty variational inequalities without increasing batch size ICLR 2023 Alternation makes the adversary weaker in two-player games NIPS 2023 Finding Actual Descent Directions for Adversarial Training ICLR 2023 Regularization of Polynomial Networks for Image Recognition CVPR 2023 What can online reinforcement learning with function approximation benefit from general coverage conditions? ICML 2023 Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks NIPS 2023 Semi Bandit dynamics in Congestion Games: Convergence to Nash Equilibrium and No-Regret Guarantees. ICML 2023 Exponential Lower Bounds for Fictitious Play in Potential Games NIPS 2023 Sample Complexity Bounds for Score-Matching: Causal Discovery and Generative Modeling NIPS 2023 DiGress: Discrete Denoising diffusion for graph generation ICLR 2023 Maximum Independent Set: Self-Training through Dynamic Programming NIPS 2023 Efficient Online Clustering with Moving Costs NIPS 2023 When do Minimax-fair Learning and Empirical Risk Minimization Coincide? ICML 2023 Understanding Deep Neural Function Approximation in Reinforcement Learning via $\epsilon$-Greedy Exploration NIPS 2022 Identifiability and generalizability from multiple experts in Inverse Reinforcement Learning NIPS 2022 Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization) NIPS 2022 On the Double Descent of Random Features Models Trained with SGD NIPS 2022 Extra-Newton: A First Approach to Noise-Adaptive Accelerated Second-Order Methods NIPS 2022 Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study NIPS 2022 Proximal Point Imitation Learning NIPS 2022 Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models ICML 2022 UnderGrad: A Universal Black-Box Optimization Method with Almost Dimension-Free Convergence Rate Guarantees ICML 2022 A Natural Actor-Critic Framework for Zero-Sum Markov Games ICML 2022 Faster One-Sample Stochastic Conditional Gradient Method for Composite Convex Minimization AISTATS 2022 Generalization Properties of NAS under Activation and Skip Connection Search NIPS 2022 High Probability Bounds for a Class of Nonconvex Algorithms with AdaGrad Stepsize ICLR 2022 The Spectral Bias of Polynomial Neural Networks ICLR 2022 Controlling the Complexity and Lipschitz Constant improves Polynomial Nets ICLR 2022 Escaping limit cycles: Global convergence for constrained nonconvex-nonconcave minimax problems ICLR 2022 Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization NIPS 2022 No-regret learning in games with noisy feedback: Faster rates and adaptivity via learning rate separation NIPS 2022 Sound and Complete Verification of Polynomial Networks NIPS 2022 Sifting through the noise: Universal first-order methods for stochastic variational inequalities NIPS 2021 The Limits of Min-Max Optimization Algorithms: Convergence to Spurious Non-Critical Sets ICML 2021 Regret Minimization in Stochastic Non-Convex Learning via a Proximal-Gradient Approach ICML 2021 STORM+: Fully Adaptive SGD with Recursive Momentum for Nonconvex Optimization NIPS 2021 The Effect of the Intrinsic Dimension on the Generalization of Quadratic Classifiers NIPS 2021 Convergence of adaptive algorithms for constrained weakly convex optimization NIPS 2021 Subquadratic Overparameterization for Shallow Neural Networks NIPS 2021 A first-order primal-dual method with adaptivity to local smoothness NIPS 2021 Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch NIPS 2021 A new regret analysis for Adam-type algorithms ICML 2020 On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems NIPS 2020 Robust Reinforcement Learning via Adversarial training with Langevin Dynamics NIPS 2020 Lipschitz constant estimation of Neural Networks via sparse polynomial optimization ICLR 2020 Convergences of Regularized Algorithms and Stochastic Gradient Methods with Random Projections JMLR 2020 Optimal Convergence for Distributed Learning with Stochastic Gradient Methods and Spectral Algorithms JMLR 2020 Random extrapolation for primal-dual coordinate descent ICML 2020 Efficient Proximal Mapping of the 1-path-norm of Shallow Networks ICML 2020 Double-Loop Unadjusted Langevin Algorithm ICML 2020 Conditional gradient methods for stochastically constrained convex minimization ICML 2020 Fast and Provable ADMM for Learning with Generative Priors NIPS 2019 UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization NIPS 2019 Iterative Classroom Teaching AAAI 2019 Almost surely constrained convex optimization ICML 2019 Finding Mixed Nash Equilibria of Generative Adversarial Networks ICML 2019 On Certifying Non-Uniform Bounds against Adversarial Attacks ICML 2019 Efficient learning of smooth probability functions from Bernoulli tests with guarantees ICML 2019 A Conditional-Gradient-Based Augmented Lagrangian Framework ICML 2019 Conditional Gradient Methods via Stochastic Path-Integrated Differential Estimator ICML 2019 Interactive Teaching Algorithms for Inverse Reinforcement Learning IJCAI 2019 Stochastic Frank-Wolfe for Composite Convex Minimization NIPS 2019 An Inexact Augmented Lagrangian Framework for Nonconvex Optimization with Nonlinear Constraints NIPS 2019 Adversarially Robust Optimization with Gaussian Processes NIPS 2018 Stochastic Three-Composite Convex Minimization with a Linear Operator AISTATS 2018 Dimension-free Information Concentration via Exp-Concavity ALT 2018 Let’s be Honest: An Optimal No-Regret Framework for Zero-Sum Games ICML 2018 Optimal Distributed Learning with Multi-pass Stochastic Gradient Methods ICML 2018 Optimal Rates of Sketched-regularized Algorithms for Least-Squares Regression over Hilbert Spaces ICML 2018 A Conditional Gradient Framework for Composite Convex Minimization with Applications to Semidefinite Programming ICML 2018 High-Dimensional Bayesian Optimization via Additive Models with Overlapping Groups AISTATS 2018 Robust Maximization of Non-Submodular Objectives AISTATS 2018 Online Adaptive Methods, Universality and Acceleration NIPS 2018 Combinatorial Penalties: Which structures are preserved by convex relaxations? AISTATS 2018 Mirrored Langevin Dynamics NIPS 2018 Streaming Robust Submodular Maximization: A Partitioned Thresholding Approach NIPS 2017 Lower Bounds on Active Learning for Graphical Model Selection AISTATS 2017 Faster Coordinate Descent via Adaptive Importance Sampling AISTATS 2017 Sketchy Decisions: Convex Low-Rank Matrix Optimization with Optimal Storage AISTATS 2017 Lower Bounds on Regret for Noisy Gaussian Process Bandit Optimization COLT 2017 Phase Transitions in the Pooled Data Problem NIPS 2017 Smooth Primal-Dual Coordinate Descent Algorithms for Nonsmooth Convex Optimization NIPS 2017 Fixed-Rank Approximation of a Positive-Semidefinite Matrix from Streaming Data NIPS 2017 Robust Submodular Maximization: A Non-Uniform Partitioning Approach ICML 2017 Limits on Sparse Support Recovery via Linear Sketching with Random Expander Matrices AISTATS 2016 An Efficient Streaming Algorithm for the Submodular Cover Problem NIPS 2016 Stochastic Three-Composite Convex Minimization NIPS 2016 Truncated Variance Reduction: A Unified Approach to Bayesian Optimization and Level-Set Estimation NIPS 2016 Time-Varying Gaussian Process Bandit Optimization AISTATS 2016 Convex Block-sparse Linear Regression with Expanders – Provably AISTATS 2016 Sparsistency of \ell_1-Regularized M-Estimators AISTATS 2015 A totally unimodular view of structured sparsity AISTATS 2015 WASP: Scalable Bayes via barycenters of subset posteriors AISTATS 2015 Composite Self-Concordant Minimization JMLR 2015 Stochastic Spectral Descent for Restricted Boltzmann Machines AISTATS 2015 A Universal Primal-Dual Convex Optimization Framework NIPS 2015 Preconditioned Spectral Descent for Deep Learning NIPS 2015 Time--Data Tradeoffs by Aggressive Smoothing NIPS 2014 Constrained convex minimization via model-based excessive gap NIPS 2014 High-Dimensional Gaussian Process Bandits NIPS 2013 Sparse projections onto the simplex ICML 2013 A proximal Newton framework for composite minimization: Graph learning without Cholesky decompositions and matrix inversions ICML 2013 Active Learning of Multi-Index Function Models NIPS 2012 Learning with Compressible Priors NIPS 2009 Sparse Signal Recovery Using Markov Random Fields NIPS 2008