Erdogdu, Murat A.
- High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation
2022/05/03 by Ba, Jimmy, Erdogdu, Murat A., Suzuki, Taiji +3 · 17 citations
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Statistics Theory (math.ST)
- Neural Networks Efficiently Learn Low-Dimensional Representations with SGD
2022/09/29 by Alireza Mousavi-Hosseini, Sejun Park, Mousavi-Hosseini, Alireza +7 · 11 citations
Computer Science · #Stochastic Gradient Optimization Techniques #Advanced Neural Network Applications #Machine Learning and ELM
- Heavy Tails in SGD and Compressibility of Overparametrized Neural Networks
2021/06/07 by Melih Barsbey, Milad Sefidgaran, Barsbey, Melih +7 · 8 citations
Computer Science · #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Stochastic Gradient Optimization Techniques
- An Analysis of Constant Step Size SGD in the Non-convex Regime: Asymptotic Normality and Bias
2020/06/14 by Lu Yu, Yu, Lu, Krishnakumar Balasubramanian +5 · 7 citations
Computer Science · Decision Sciences · Mathematics · #Stochastic Gradient Optimization Techniques #Advanced Bandit Algorithms Research #Markov Chains and Monte Carlo Methods
- Normal Approximation for Stochastic Gradient Descent via Non-Asymptotic Rates of Martingale CLT
2019/04/03 by Andreas Anastasiou, Krishnakumar Balasubramanian, Anastasiou, Andreas +3 · 5 citations
Computer Science · Mathematics · #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (stat.ML) #Markov Chains and Monte Carlo Methods #Optimization and Control (math.OC) #Probability (math.PR) #Random Matrices and Applications #Statistics Theory (math.ST) #Stochastic Gradient Optimization Techniques
- Towards a Theory of Non-Log-Concave Sampling: First-Order Stationarity Guarantees for Langevin Monte Carlo
2022/02/10 by Krishnakumar Balasubramanian, Sinho Chewi, Balasubramanian, Krishnakumar +7 · 6 citations
Engineering · Mathematics · #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (stat.ML) #Markov Chains and Monte Carlo Methods #Sparse and Compressive Sensing Techniques #Statistical Methods and Inference #Statistics Theory (math.ST)
- On the Convergence of Langevin Monte Carlo: The Interplay between Tail Growth and Smoothness
2020/05/27 by Murat A. Erdogdu, Erdogdu, Murat A., Rasa Hosseinzadeh +1 · 5 citations
Mathematics · Physics and Astronomy · #Markov Chains and Monte Carlo Methods #Statistical Mechanics and Entropy #Stochastic processes and statistical mechanics
- Convergence of Langevin Monte Carlo in Chi-Squared and Renyi Divergence
2020/07/22 by Murat A. Erdogdu, Erdogdu, Murat A., Rasa Hosseinzadeh +3 · 4 citations
Mathematics · Medicine · #Advanced Neuroimaging Techniques and Applications #Computation (stat.CO) #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Markov Chains and Monte Carlo Methods #Point processes and geometric inequalities #Probability (math.PR)
- Convergence rates of sub-sampled Newton methods
2015/08/12 by Erdogdu, Murat A., Montanari, Andrea · 3 citations
#FOS: Computer and information sciences #Machine Learning (stat.ML)
- Mirror Descent Strikes Again: Optimal Stochastic Convex Optimization under Infinite Noise Variance
2022/02/23 by N. Mert Vural, Vural, Nuri Mert, Yu Lu +7 · 5 citations
Computer Science · Decision Sciences · Engineering · #Advanced Bandit Algorithms Research #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC) #Sparse and Compressive Sensing Techniques #Stochastic Gradient Optimization Techniques
- Manipulating SGD with Data Ordering Attacks
2021/04/19 by Shumailov, Ilia, Shumaylov, Zakhar, Kazhdan, Dmitry +4 · 3 citations
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Towards a Complete Analysis of Langevin Monte Carlo: Beyond Poincaré Inequality
2023/03/07 by Mousavi-Hosseini, Alireza, Farghly, Tyler, He, Ye +2 · 4 citations
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (stat.ML) #Probability (math.PR) #Statistics Theory (math.ST)
- Gradient-Based Feature Learning under Structured Data
2023/09/07 by Alireza Mousavi-Hosseini, Mousavi-Hosseini, Alireza, Denny Wu +5 · 5 citations
Computer Science · Environmental Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Hydrological Forecasting Using AI #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Convergence Rates of Stochastic Gradient Descent under Infinite Noise Variance
2021/02/20 by Hongjian Wang, Wang, Hongjian, Mert Gürbüzbalaban +7 · 3 citations
Computer Science · Engineering · Mathematics · #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (stat.ML) #Optimization and Control (math.OC) #Random Matrices and Applications #Sparse and Compressive Sensing Techniques #Stochastic Gradient Optimization Techniques
- Stochastic Runge-Kutta Accelerates Langevin Monte Carlo and Beyond
2019/06/19 by Li, Xuechen, Wu, Denny, Mackey, Lester +1 · 2 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- On the Ergodicity, Bias and Asymptotic Normality of Randomized Midpoint Sampling Method
2020/11/06 by Ye He, Krishnakumar Balasubramanian, He, Ye +3 · 2 citations
Mathematics · #Computation (stat.CO) #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Markov Chains and Monte Carlo Methods #Point processes and geometric inequalities #Statistical Methods and Inference #Statistics Theory (math.ST)
- On Empirical Risk Minimization with Dependent and Heavy-Tailed Data
2021/09/06 by Abhishek Roy, Roy, Abhishek, Krishnakumar Balasubramanian +3 · 2 citations
Mathematics · Decision Sciences · #Statistical Methods and Inference #Markov Chains and Monte Carlo Methods #Risk and Portfolio Optimization
- Mean-Square Analysis of Discretized Itô Diffusions for Heavy-tailed Sampling
2023/03/01 by Ye He, He, Ye, Tyler Farghly +5 · 2 citations
Engineering · Mathematics · #Computation (stat.CO) #FOS: Computer and information sciences #FOS: Mathematics #Geometric Analysis and Curvature Flows #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Markov Chains and Monte Carlo Methods #Numerical Analysis (math.NA) #Sparse and Compressive Sensing Techniques #Statistics Theory (math.ST)
- Flexible results for quadratic forms with applications to variance\n components estimation
2015/09/14 by Lee H. Dicker, Murat A. Erdogdu, Dicker, Lee H. +1 · 1 citation
Computer Science · Mathematics · #Bayesian Methods and Mixture Models #FOS: Mathematics #Statistical Methods and Bayesian Inference #Statistical Methods and Inference #Statistics Theory (math.ST)
- Robust Feature Learning for Multi-Index Models in High Dimensions
2024/10/21 by Mousavi-Hosseini, Alireza, Javanmard, Adel, Erdogdu, Murat A. · 4 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Inference in Graphical Models via Semidefinite Programming Hierarchies
2017/09/19 by Murat A. Erdogdu, Erdogdu, Murat A., Yash Deshpande +3 · 1 citation
Computer Science · #Bayesian Modeling and Causal Inference #Data Structures and Algorithms (cs.DS) #Error Correcting Code Techniques #FOS: Computer and information sciences #Machine Learning (stat.ML) #Machine Learning and Algorithms
- Convergence Rate of Block-Coordinate Maximization Burer-Monteiro Method for Solving Large SDPs
2018/07/12 by Erdogdu, Murat A., Ozdaglar, Asuman, Parrilo, Pablo A. +1 · 1 citation
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC)
- Sampling from the Mean-Field Stationary Distribution
2024/02/12 by Kook, Yunbum, Zhang, Matthew S., Chewi, Sinho +2 · 2 citations
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Statistics Theory (math.ST)
- A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers
2024/05/27 by He, Ye, Mousavi-Hosseini, Alireza, Balasubramanian, Krishnakumar +1 · 2 citations
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (stat.ML) #Statistics Theory (math.ST)
- Riemannian Langevin Algorithm for Solving Semidefinite Programs
2020/10/21 by Li, Mufan Bill, Erdogdu, Murat A. · 1 citation
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC)
- Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics
2024/08/14 by Alireza Mousavi-Hosseini, Denny Wu, Mousavi-Hosseini, Alireza +3 · 3 citations
Computer Science · #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications
- Heavy-tailed Sampling via Transformed Unadjusted Langevin Algorithm
2022/01/20 by He, Ye, Balasubramanian, Krishnakumar, Erdogdu, Murat A. · 1 citation
#Computation (stat.CO) #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (stat.ML) #Statistics Theory (math.ST)
- Improved Discretization Analysis for Underdamped Langevin Monte Carlo
2023/02/16 by Zhang, Matthew, Chewi, Sinho, Li, Mufan Bill +2 · 1 citation
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (stat.ML) #Statistics Theory (math.ST)
- Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning
2023/07/04 by Kastner, Tyler, Erdogdu, Murat A., Farahmand, Amir-massoud · 1 citation
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective
2025/03/14 by Alireza Mousavi-Hosseini, Clayton Sanford, Mousavi-Hosseini, Alireza +5 · 1 voice · 1 citation
#stat.ML #cs.LG
- On the Efficiency of ERM in Feature Learning
2024/11/18 by Hanchi, Ayoub El, Maddison, Chris J., Erdogdu, Murat A. · 1 citation
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Statistics Theory (math.ST)
- Minimax Linear Regression under the Quantile Risk
2024/06/17 by Ayoub El Hanchi, Chris J. Maddison, Hanchi, Ayoub El +3 · 1 citation
Mathematics · #Advanced Statistical Methods and Models #Statistical Methods and Inference