Thrampoulidis, Christos

54 publications

TMLR 2026 Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy Gradients Christos Thrampoulidis, Sadegh Mahdavi, Wenlong Deng

ICLR 2026 How Muon’s Spectral Design Benefits Generalization: A Study on Imbalanced Data Bhavya Vasudeva, Puneesh Deora, Yize Zhao, Vatsal Sharan, Christos Thrampoulidis

ICLR 2026 Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning Wenlong Deng, Yi Ren, Yushu Li, Boying Gong, Danica J. Sutherland, Xiaoxiao Li, Christos Thrampoulidis

ICLRW 2025 Can Transformers Learn Tasks of Varying Complexity In-Context? Puneesh Deora, Bhavya Vasudeva, Tina Behnia, Christos Thrampoulidis

ICLR 2025 DARE the Extreme: Revisiting Delta-Parameter Pruning for Fine-Tuned Models Wenlong Deng, Yize Zhao, Vala Vakilian, Minghui Chen, Xiaoxiao Li, Christos Thrampoulidis

TMLR 2025 Implicit Bias and Fast Convergence Rates for Self-Attention Bhavya Vasudeva, Puneesh Deora, Christos Thrampoulidis

NeurIPS 2025 Implicit Bias of Spectral Descent and Muon on Multiclass Separable Data Chen Fan, Mark Schmidt, Christos Thrampoulidis

ICML 2025 Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant Evaluation Sadegh Mahdavi, Muchen Li, Kaiwen Liu, Christos Thrampoulidis, Leonid Sigal, Renjie Liao

NeurIPS 2025 On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization Wenlong Deng, Yi Ren, Muchen Li, Danica J. Sutherland, Xiaoxiao Li, Christos Thrampoulidis

ICLR 2025 Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods Hossein Taheri, Christos Thrampoulidis, Arya Mazumdar

NeurIPS 2025 Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining Nathan Stromberg, Christos Thrampoulidis, Lalitha Sankar

AAAI 2024 Class-Attribute Priors: Adapting Optimization to Heterogeneity and Fairness Objective Xuechen Zhang, Mingchen Li, Jiasi Chen, Christos Thrampoulidis, Samet Oymak

AAAI 2024 Engineering the Neural Collapse Geometry of Supervised-Contrastive Loss (Student Abstract) Jaidev Gill, Vala Vakilian, Christos Thrampoulidis

JMLR 2024 Generalization and Stability of Interpolating Neural Networks with Minimal Width Hossein Taheri, Christos Thrampoulidis

NeurIPS 2024 Implicit Optimization Bias of Next-Token Prediction in Linear Models Christos Thrampoulidis

ICMLW 2024 Implicit Optimization Bias of Next-Token Prediction in Linear Models Christos Thrampoulidis

ICMLW 2024 Implicit Optimization Bias of Next-Token Prediction in Linear Models Christos Thrampoulidis

ICLR 2024 Memorization Capacity of Multi-Head Attention in Transformers Sadegh Mahdavi, Renjie Liao, Christos Thrampoulidis

TMLR 2024 On the Optimization and Generalization of Multi-Head Attention Puneesh Deora, Rouzbeh Ghaderi, Hossein Taheri, Christos Thrampoulidis

ICLR 2024 Symmetric Neural-Collapse Representations with Supervised Contrastive Loss: The Impact of ReLU and Batching Ganesh Ramachandra Kini, Vala Vakilian, Tina Behnia, Jaidev Gill, Christos Thrampoulidis

CVPR 2024 Unlocking the Potential of Prompt-Tuning in Bridging Generalized and Personalized Federated Learning Wenlong Deng, Christos Thrampoulidis, Xiaoxiao Li

NeurIPS 2023 BiSLS/SPS: Auto-Tune Step Sizes for Stable Bi-Level Optimization Chen Fan, Gaspard Choné-Ducasse, Mark Schmidt, Christos Thrampoulidis

AAAI 2023 Fast Convergence in Learning Two-Layer Neural Networks with Separable Data Hossein Taheri, Christos Thrampoulidis

ECML-PKDD 2023 Fast Convergence of Random Reshuffling Under Over-Parameterization and the Polyak-Łojasiewicz Condition Chen Fan, Christos Thrampoulidis, Mark Schmidt

NeurIPSW 2023 MSL: An Adaptive Momentem-Based Stochastic Line-Search Framework Chen Fan, Sharan Vaswani, Christos Thrampoulidis, Mark Schmidt

AISTATS 2023 On Generalization of Decentralized Learning with Separable Data Hossein Taheri, Christos Thrampoulidis

AISTATS 2023 On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data Tina Behnia, Ganesh Ramachandra Kini, Vala Vakilian, Christos Thrampoulidis

ICML 2023 On the Role of Attention in Prompt-Tuning Samet Oymak, Ankit Singh Rawat, Mahdi Soltanolkotabi, Christos Thrampoulidis

ICLRW 2023 On the Role of Attention in Prompt-Tuning Samet Oymak, Ankit Singh Rawat, Mahdi Soltanolkotabi, Christos Thrampoulidis

TMLR 2023 Towards Better Out-of-Distribution Generalization of Neural Algorithmic Reasoning Tasks Sadegh Mahdavi, Kevin Swersky, Thomas Kipf, Milad Hashemi, Christos Thrampoulidis, Renjie Liao

NeurIPSW 2023 Transformers as Support Vector Machines Davoud Ataee Tarzanagh, Yingcong Li, Christos Thrampoulidis, Samet Oymak

NeurIPSW 2022 Fast Convergence of Random Reshuffling Under Interpolation and the Polyak-\l Ojasiewicz Condition Chen Fan, Christos Thrampoulidis, Mark Schmidt

ICML 2022 FedNest: Federated Bilevel, Minimax, and Compositional Optimization Davoud Ataee Tarzanagh, Mingchen Li, Christos Thrampoulidis, Samet Oymak

NeurIPS 2022 Imbalance Trouble: Revisiting Neural-Collapse Geometry Christos Thrampoulidis, Ganesh Ramachandra Kini, Vala Vakilian, Tina Behnia

NeurIPS 2022 Mirror Descent Maximizes Generalized Margin and Can Be Implemented Efficiently Haoyuan Sun, Kwangjun Ahn, Christos Thrampoulidis, Navid Azizan

NeurIPSW 2022 On Generalization of Decentralized Learning with Separable Data Hossein Taheri, Christos Thrampoulidis

NeurIPSW 2022 On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data Tina Behnia, Ganesh Ramachandra Kini, Vala Vakilian, Christos Thrampoulidis

AISTATS 2021 Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions Hossein Taheri, Ramtin Pedarsani, Christos Thrampoulidis

NeurIPS 2021 AutoBalance: Optimized Loss Functions for Imbalanced Data Mingchen Li, Xuechen Zhang, Christos Thrampoulidis, Jiasi Chen, Samet Oymak

NeurIPS 2021 Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation Ke Wang, Vidya Muthukumar, Christos Thrampoulidis

AAAI 2021 Decentralized Multi-Agent Linear Bandits with Safety Constraints Sanae Amani, Christos Thrampoulidis

NeurIPS 2021 Label-Imbalanced and Group-Sensitive Classification Under Overparameterization Ganesh Ramachandra Kini, Orestis Paraskevas, Samet Oymak, Christos Thrampoulidis

AAAI 2021 Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks Xiangyu Chang, Yingcong Li, Samet Oymak, Christos Thrampoulidis

ICML 2021 Safe Reinforcement Learning with Linear Function Approximation Sanae Amani, Christos Thrampoulidis, Lin Yang

NeurIPS 2021 UCB-Based Algorithms for Multinomial Logistic Regression Bandits Sanae Amani, Christos Thrampoulidis

L4DC 2020 Regret Bound for Safe Gaussian Process Bandit Optimization Sanae Amani, Mahnoosh Alizadeh, Christos Thrampoulidis

AISTATS 2020 Sharp Asymptotics and Optimal Performance for Inference in Binary Models Hossein Taheri, Ramtin Pedarsani, Christos Thrampoulidis

NeurIPS 2020 Stage-Wise Conservative Linear Bandits Ahmadreza Moradipari, Christos Thrampoulidis, Mahnoosh Alizadeh

NeurIPS 2020 Theoretical Insights into Multiclass Classification: A High-Dimensional Asymptotic View Christos Thrampoulidis, Samet Oymak, Mahdi Soltanolkotabi

AISTATS 2019 Lifting High-Dimensional Non-Linear Models with Gaussian Regressors Christos Thrampoulidis, Ankit Singh Rawat

NeurIPS 2019 Linear Stochastic Bandits Under Safety Constraints Sanae Amani, Mahnoosh Alizadeh, Christos Thrampoulidis

CVPR 2019 Using Unknown Occluders to Recover Hidden Scenes Adam B. Yedidia, Manel Baradad, Christos Thrampoulidis, William T. Freeman, Gregory W. Wornell

NeurIPS 2015 LASSO with Non-Linear Measurements Is Equivalent to One with Linear Measurements Christos Thrampoulidis, Ehsan Abbasi, Babak Hassibi

COLT 2015 Regularized Linear Regression: A Precise Analysis of the Estimation Error Christos Thrampoulidis, Samet Oymak, Babak Hassibi