activity
20182021
most citedDoubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information

3 citations · 5 across the 3 of their papers we have counts for

collaborators

6 papers

cs.LG20213 cited

Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information

Majid Jahani, Sergey Rusakov, Zheng Shi +3

We present a novel adaptive optimization algorithm for large-scale machine learning problems. Equipped with a low-cost estimate of local curvature and Lipschitz smoothness, our met…

cs.LG2020

DynNet: Physics-based neural architecture design for linear and nonlinear structural response modeling and prediction

Soheil Sadeghi Eshkevari, Martin Takáč, Shamim N. Pakzad +1

Data-driven models for predicting dynamic responses of linear and nonlinear systems are of great importance due to their wide application from probabilistic analysis to inverse pro…

math.OC20201 cited

SONIA: A Symmetric Blockwise Truncated Optimization Algorithm

Majid Jahani, Mohammadreza Nazari, Rachael Tappenden +2

This work presents a new algorithm for empirical risk minimization. The algorithm bridges the gap between first- and second-order methods by computing a search direction that uses…

cs.LG20191 cited

Don't Forget Your Teacher: A Corrective Reinforcement Learning Framework

Mohammadreza Nazari, Majid Jahani, Lawrence V. Snyder +1

Although reinforcement learning (RL) can provide reliable solutions in many settings, practitioners are often wary of the discrepancies between the RL solution and their status quo…

math.OC2019

Scaling Up Quasi-Newton Algorithms: Communication Efficient Distributed SR1

Majid Jahani, Mohammadreza Nazari, Sergey Rusakov +2

In this paper, we present a scalable distributed implementation of the Sampled Limited-memory Symmetric Rank-1 (S-LSR1) algorithm. First, we show that a naive distributed implement…

cs.LG2018

Efficient Distributed Hessian Free Algorithm for Large-scale Empirical Risk Minimization via Accumulating Sample Strategy

Majid Jahani, Xi He, Chenxin Ma +4

In this paper, we propose a Distributed Accumulated Newton Conjugate gradiEnt (DANCE) method in which sample size is gradually increasing to quickly obtain a solution whose empiric…