91 citations · 108 across the 6 of their papers we have counts for
8 papers
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…
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…
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…
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…
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…
Quasi-Newton Methods for Machine Learning: Forget the Past, Just Sample
Albert S. Berahas, Majid Jahani, Peter Richtárik +1
We present two sampled quasi-Newton methods (sampled LBFGS and sampled LSR1) for solving empirical risk minimization problems that arise in machine learning. Contrary to the classi…
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…
Fast and Safe: Accelerated gradient methods with optimality certificates and underestimate sequences
Majid Jahani, Naga Venkata C. Gudapati, Chenxin Ma +2
In this work we introduce the concept of an Underestimate Sequence (UES), which is motivated by Nesterov's estimate sequence. Our definition of a UES utilizes three sequences, one…