Samet Oymak

AdMiT: Adaptive Multi-Source Tuning in Dynamic Environments CVPR 2025 Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition ICML 2025 High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws ICLR 2025 On the Power of Convolution-Augmented Transformer AAAI 2025 Provable Benefits of Task-Specific Prompts for In-context Learning AISTATS 2025 Test-Time Training Provably Improves Transformers as In-context Learners ICML 2025 TimePFN: Effective Multivariate Time Series Forecasting with Synthetic Data AAAI 2025 A Score-Based Deterministic Diffusion Algorithm with Smooth Scores for General Distributions AAAI 2024 Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks ICML 2024 Class-Attribute Priors: Adapting Optimization to Heterogeneity and Fairness Objective AAAI 2024 CONTRAST: Continual Multi-source Adaptation to Dynamic Distributions NeurIPS 2024 Effective Restoration of Source Knowledge in Continual Test Time Adaptation WACV 2024 Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning NeurIPS 2024 Fine-grained Analysis of In-context Linear Estimation: Data, Architecture, and Beyond NeurIPS 2024 From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers ICML 2024 Mechanics of Next Token Prediction with Self-Attention AISTATS 2024 Selective Attention: Enhancing Transformer through Principled Context Control NeurIPS 2024 Understanding Inverse Scaling and Emergence in Multitask Representation Learning AISTATS 2024 Dissecting Chain-of-Thought: Compositionality through In-Context Filtering and Learning NeurIPS 2023 Learning on Manifolds: Universal Approximations Properties using Geometric Controllability Conditions for Neural ODEs L4DC 2023 Max-Margin Token Selection in Attention Mechanism NeurIPS 2023 On the Role of Attention in Prompt-tuning ICML 2023 Provable Pathways: Learning Multiple Tasks over Multiple Paths AAAI 2023 Stochastic Contextual Bandits with Long Horizon Rewards AAAI 2023 Transformers as Algorithms: Generalization and Stability in In-context Learning ICML 2023 FedNest: Federated Bilevel, Minimax, and Compositional Optimization ICML 2022 Non-asymptotic and Accurate Learning of Nonlinear Dynamical Systems JMLR 2022 A Theoretical Characterization of Semi-supervised Learning with Self-training for Gaussian Mixture Models AISTATS 2021 AutoBalance: Optimized Loss Functions for Imbalanced Data NeurIPS 2021 Generalization Guarantees for Neural Architecture Search with Train-Validation Split ICML 2021 Label-Imbalanced and Group-Sensitive Classification under Overparameterization NeurIPS 2021 Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks AAAI 2021 Towards Sample-efficient Overparameterized Meta-learning NeurIPS 2021 Unsupervised Multi-Source Domain Adaptation Without Access to Source Data CVPR 2021 Finite Sample System Identification: Optimal Rates and the Role of Regularization L4DC 2020 Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks AISTATS 2020 Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View NeurIPS 2020 Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path? ICML 2019 Stochastic Gradient Descent Learns State Equations with Nonlinear Activations COLT 2019 Learning Compact Neural Networks with Regularization ICML 2018 Parallel Correlation Clustering on Big Graphs NeurIPS 2015 Regularized Linear Regression: A Precise Analysis of the Estimation Error COLT 2015 Graph Clustering With Missing Data: Convex Algorithms and Analysis NeurIPS 2014