News travels fast in places where nothing much ever happens.
Charles Bukowski
2021
-
April 2021: Presented in the Statistics Seminar at UW Madison (Department of Statistics)
-
April 2021: Presented in a session organized by Giampaolo Luizzi (Optimization in Machine Learning) at the 3rd IMA and OR Society Conference on Mathematics of Operational Research (IMA ORS)
-
April 2021: Our ICML 2020 workshop “Beyond First Order Methods in Machine Learning Systems“ (co-organizers Raghu Bollapragrada, Rixon Crane, Amir Gholami, J. Lyle Kim, Anastasios (Tasos) Kyrillidis, and Michael Mahoney, Fred Roosta, Rachael Tappenden) has been accepted (all past workshops can be found here)
-
March 2021: Our paper “A Theoretical and Empirical Comparison of Gradient Approximations in Derivative-Free Optimization“ (joint work with Liyuan Cao, Krzysztof Choromanski and Katya Scheinberg) has been accepted for publication in Foundations of Computational Mathematics
-
March 2021: Our paper “Global Convergence Rate Analysis of a Generic Line Search Algorithm with Noise“ (joint work with Liyuan Cao and Katya Scheinberg) has been accepted for publication in SIAM Journal on Optimization
-
March 2021: Presented in a session organized by Amir Gholaminejad, Fred Roosta and Michael Mahoney (Beyond First Order Methods in Machine Learning Systems) at the SIAM CSE 2021
-
February 2021: Organized the IOE department seminars this semester
-
February 2021: Our paper “SONIA: A Symmetric Blockwise Truncated Optimization Algorithm“ (joint work with Majid Jahani, Mohammadreza Nazari, Rachael Tappenden and Martin Takáč) has been accepted for publication at the 24th International Conference on Artificial Intelligence and Statistics (AISTATS 2021)
-
January 2021: Our paper “Limited-Memory BFGS with Displacement Aggregation“ (joint work with Frank E. Curtis and Baoyu Zhou) has been accepted for publication in Mathematical Programming
2020
-
December 2020: Elected INFORMS Optimization Society Vice Chair for Nonlinear Optimization
-
November 2020: Organized four sessions (Methods for Large Scale, Nonlinear and Stochastic Optimization I/II/III/IV) at the INFORMS Annual Meeting
-
November 2020: Presented in a session organized by Siqian Shen (Computational Methods for Large-scale Stochastic Programs) at the INFORMS Annual Meeting
-
September 2020: Our paper “Finite Difference Neural Networks: Fast Prediction of Partial Differential Equations“ (joint work with Zheng Shi, Nur Sila Gulgec, Shamim N. Pakzad and Martin Takáč) has been accepted for publication at the 19th IEEE International Conference on Machine Learning and Applications (IEEE-ICMLA 2020)
-
September 2020: Presented in the MIDAS (Michigan Institute for Data Science) Faculty Pitch Presentations (link)
-
September 2020: Became an Affiliated Faculty member of MIDAS (Michigan Institute for Data Science) and MICDE (Michigan Institute of for Computational Discovery and Engineering)
-
August 2020: Officially joined the Department of Industrial & Operations Engineering at the University of Michigan as an Assistant Professor (faculty profile, IOE news)
-
July 2020: New paper “Sequential Quadratic Optimization for Nonlinear Equality Constrained Stochastic Optimization“ (joint work with Frank E. Curtis, Daniel P. Robinson and Baoyu Zhou)
-
June 2020: New paper “SONIA: A Symmetric Blockwise Truncated Optimization Algorithm“ (joint work with Majid Jahani, Mohammadreza Nazari, Rachael Tappenden and Martin Takáč)
-
June 2020: New paper “Finite Difference Neural Networks: Fast Prediction of Partial Differential Equations“ (joint work with Zheng Shi, Nur Sila Gulgec, Shamim N. Pakzad and Martin Takáč)
-
May 2020: New paper “On the Convergence of Nested Decentralized Gradient Methods with Multiple Consensus and Gradient Steps“ (joint work with Raghu Bollapragada and Ermin Wei)
-
May 2020: Our paper “Scaling Up Quasi-Newton Algorithms: Communication Efficient Distributed SR1“ (joint work with Majid Jahani, Mohammadreza Nazari, Sergey Rusakov and Martin Takáč) has been accepted for publication at The Sixth International Conference on Machine Learning, Optimization, and Data Science
-
March 2020: Our ICML 2020 workshop “Beyond First Order Methods in Machine Learning Systems“ (co-organizers Amir Gholami, Anastasios (Tasos) Kyrillidis, Fred Roosta and Michael Mahoney) has been accepted (all past workshops can be found here)
-
February 2020: Invited to present at the DataX Workshop: Old and New Open Questions in Optimization at Princeton University
-
February 2020: Our paper “An Investigation of Newton-Sketch and Subsampled Newton Methods“ (joint work with Raghu Bollapragada and Jorge Nocedal) has been accepted for publication in Optimization Methods and Software
-
February 2020: I will be joining the Department of Industrial & Operations Engineering at the University of Michigan as an Assistant Professor in August 2020.
-
January 2020: Presented in a session organized by Luis Tenorio and Stephen Becker (Derivative Free Optimization for High-Dimensional Problems) at the Joint Mathematics Meetings, Denver, CO
-
January 2020: Invited to be the chair of the organizing committee of the Modeling and Optimization: Theory and Applications (MOPTA) 2020 conference at Lehigh University
2019
-
December 2019: Videos from our NeurIPS workshop “Beyond First Order Methods in Machine Learning Systems“ are online
-
November 2019: Presented in the Numerical Analysis and Scientific Computing Seminar at the Courant Institute of Mathematical Sciences, New York University (invited by Michael Overton)
-
October 2019: Presented in a session organized by Raghu Bollapragada (Recent Developments in Optimization for Machine Learning) at the INFORMS Annual Meeting, Seattle, WA
-
October 2019: Organized four sessions (Methods for Large Scale, Nonlinear and Stochastic Optimization I/II/III/IV) at the INFORMS Annual Meeting, Seattle, WA
-
October 2019: New paper “Global Convergence Rate Analysis of a Generic Line Search Algorithm with Noise“ (joint work with Liyuan Cao and Katya Scheinberg)
-
October 2019: Presented at the ORIE Young Researchers workshop at Cornell University, Ithaca, NY
-
August 2019: Our paper “A Robust Multi-Batch L-BFGS Method for Machine Learning“ (joint work with Martin Takáč) has been accepted for publication in Optimization Methods and Software
-
August 2019: Organized four sessions (Nonlinear and Stochastic Optimization I/II/III/IV) at the Sixth International Conference on Continuous Optimization, Berlin, Germany
-
August 2019: Organized four sessions (Recent Advancements in Optimization Methods for Machine Learning I/II/III/IV) at the Sixth International Conference on Continuous Optimization, Berlin, Germany
-
August 2019: Presented in a session (Nonlinear and Stochastic Optimization IV) at the Sixth International Conference on Continuous Optimization, Berlin, Germany
-
July 2019: Our NeurIPS 2019 workshop “Beyond First Order Methods in Machine Learning Systems“ (co-organizers Anastasios (Tasos) Kyrillidis, Fred Roosta and Michael Mahoney) has been accepted
-
July 2019: Our paper “Nested Distributed Gradient Methods with Adaptive Quantized Communication“ (joint work with Ermin Wei and Charikleia Iakovidou) has been accepted for publication at the 58th Conference on Decision and Control
-
June 2019: New paper “Linear interpolation gives better gradients than Gaussian smoothing in derivative-free optimization“ (joint work with Liyuan Cao, Krzysztof Choromanski and Katya Scheinberg)
-
June 2019: New paper “Scaling Up Quasi-Newton Algorithms: Communication Efficient Distributed SR1“ (joint work with Majid Jahani, Mohammadreza Nazari, Sergey Rusakov and Martin Takáč)
-
May 2019: New paper “A Theoretical and Empirical Comparison of Gradient Approximations in Derivative-Free Optimization“ (joint work with Liyuan Cao, Krzysztof Choromanski and Katya Scheinberg)
-
March 2019: New paper “Limited-Memory BFGS with Displacement Aggregation“ (joint work with Frank E. Curtis and Baoyu Zhou)
-
March 2019: New paper “Nested Distributed Gradient Methods with Adaptive Quantized Communication“ (joint work with Ermin Wei and Charikleia Iakovidou)
-
February 2019: Presented in a session organized by Juliane Mueller and Matt Menickelly (Derivative-free and Global Optimization) at the SIAM Conference on Computational Science and Engineering, Spokane, WA
-
January 2019: New paper “Quasi-Newton Methods for Deep Learning: Forget the Past, Just Sample“ (joint work with Majid Jahani and Martin Takáč)
2018
- December 2018: Our paper “Derivative-Free Optimization of Noisy Functions via Quasi-Newton Methods“ (joint work with Jorge Nocedal and Richard H. Byrd) has been accepted for publication in SIAM Journal on Optimization
-
November 2018: Presented in a session organized by Lam M. Nguyen (Recent Advances in Optimization Methods for Machine Learning) at the INFORMS Annual Meeting, Phoenix, AZ
-
November 2018: Organized two sessions (Methods for Large Scale Nonlinear and Stochastic Optimization I/II) at the INFORMS Annual Meeting, Phoenix, AZ
-
October 2018: Attended the Second TRIPODS PI workshop at the University of California, Santa Cruz – Silicon Valley Campus
-
October 2018: Our paper “Balancing Communication and Computation in Distributed Optimization“ (joint work with Raghu Bollapragada, Nitish Shirish Keskar and Ermin Wei) has been accepted for publication in IEEE Transactions on Automatic Control.
-
September 2018: Joined the ISE department at Lehigh University as a postdoctoral research fellow working with Professors Katya Scheinberg, Frank Curtis and Martin Takáč
-
August 2018: Presented at the DIMACS/TRIPODS/MOPTA conference at Lehigh University
-
July 2018: Presented in a session organized by Professor Nocedal (Stochastic and Nonlinear Optimization) at ISMP, Bordeaux, France
-
March 2018: Started a postdoctoral research fellowship in the IEMS department at Northwestern University working with Professor Nocedal
- February 2018: Successfully defended my PhD!