7 papers · 1 filter
Generalized Random Direction Newton Algorithms for Stochastic Optimization
Soumen Pachal, Prashanth L. A., Shalabh Bhatnagar +1
We present a family of generalized Hessian estimators of the objective using random direction stochastic approximation (RDSA) by utilizing only noisy function measurements. The for…
Reinforcement learning with an expectile-based objective
Sumedh Gupte, Shrey Rakeshkumar Patel, Soumen Pachal +2
We consider the policy evaluation and control in a finite horizon reinforcement learning (RL) setting under an expectile-based objective. First, we derive the mean-squared error (M…
Policy Newton methods for Distortion Riskmetrics
Soumen Pachal, Mizhaan Prajit Maniyar, Prashanth L. A
We consider the problem of risk-sensitive control in a reinforcement learning (RL) framework. In particular, we aim to find a risk-optimal policy by maximizing the distortion riskm…
Generalized Simultaneous Perturbation-based Gradient Search with Reduced Estimator Bias
Soumen Pachal, Shalabh Bhatnagar, L. A. Prashanth
We present in this paper a family of generalized simultaneous perturbation-based gradient search (GSPGS) estimators that use noisy function measurements. The number of function mea…
Public Transit Arrival Prediction: a Seq2Seq RNN Approach
Nancy Bhutani, Soumen Pachal, Avinash Achar
Arrival/Travel times for public transit exhibit variability on account of factors like seasonality, dwell times at bus stops, traffic signals, travel demand fluctuation etc. The de…
Sequence Prediction Under Missing Data : An RNN Approach Without Imputation
Soumen Pachal, Avinash Achar
Missing data scenarios are very common in ML applications in general and time-series/sequence applications are no exceptions. This paper pertains to a novel Recurrent Neural Networ…
Seasonal Encoder-Decoder Architecture for Forecasting
Avinash Achar, Soumen Pachal
Deep learning (DL) in general and Recurrent neural networks (RNNs) in particular have seen high success levels in sequence based applications. This paper pertains to RNNs for time…