← Authors

Samet Oymak

43 papers · 2014–2025 · 10 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (10) 🐝 Cross-Pollinator (13) 🐣 Hot Topic Early Bird πŸƒ Academic Marathon (11) 🌈 Renaissance Researcher (6) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (19) 🧭 Keyword Pioneer 🀝 Dynamic Duo (10) πŸ† Grand Slam ❓ The Questioner (2) πŸ—ƒοΈ Keyword Collector (60) πŸš€ Conference Pioneer πŸ”₯ Unstoppable (8) ⚑ Prolific Year (11) πŸ’Ž Century Club (43)

Conferences

NIPS (12) ICML (10) AAAI (7) AISTATS (5) COLT (2) CVPR (2) L4DC (2) ICLR (1) JMLR (1) WACV (1)

Top co-authors

Yingcong Li (10) Xuechen Zhang (9) CHRISTOS THRAMPOULIDIS (8) Mingchen Li (7) Mahdi Soltanolkotabi (6) Dimitris Papailiopoulos (5) Xiangyu Chang (5) Muhammed Emrullah Ildiz (5) Jiasi Chen (4) Sk Miraj Ahmed (4)

Keywords

gradient descent (8) sample complexity (6) attention mechanism (5) neural network (3) in-context learning (3) generalization bound (3) transformer architecture (3) few-shot learning (3) support vector machine (3) large language model (2) bilevel optimization (2) language modeling (2) representation learning (2) loss function (2) model selection (2) graph clustering (2) model compression (2) continual learning (2) domain adaptation (2) feature learning (1)

Papers

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