activity
20162022
most citedLSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection

347 citations · 494 across the 10 of their papers we have counts for

collaborators

18 papers

cs.LG2022

Continual Learning for Multivariate Time Series Tasks with Variable Input Dimensions

Vibhor Gupta, Jyoti Narwariya, Pankaj Malhotra +2

We consider a sequence of related multivariate time series learning tasks, such as predicting failures for different instances of a machine from time series of multi-sensor data, o…

cs.LG2022

Learning to Liquidate Forex: Optimal Stopping via Adaptive Top-K Regression

Diksha Garg, Pankaj Malhotra, Anil Bhatia +3

We consider learning a trading agent acting on behalf of the treasury of a firm earning revenue in a foreign currency (FC) and incurring expenses in the home currency (HC). The goa…

cs.LG2022

Electricity Consumption Forecasting for Out-of-distribution Time-of-Use Tariffs

Jyoti Narwariya, Chetan Verma, Pankaj Malhotra +3

In electricity markets, retailers or brokers want to maximize profits by allocating tariff profiles to end consumers. One of the objectives of such demand response management is to…

cs.LG2021

Systematic Generalization in Neural Networks-based Multivariate Time Series Forecasting Models

Hritik Bansal, Gantavya Bhatt, Pankaj Malhotra +1

Systematic generalization aims to evaluate reasoning about novel combinations from known components, an intrinsic property of human cognition. In this work, we study systematic gen…

cs.LG20208 cited

Batch-Constrained Distributional Reinforcement Learning for Session-based Recommendation

Diksha Garg, Priyanka Gupta, Pankaj Malhotra +2

Most of the existing deep reinforcement learning (RL) approaches for session-based recommendations either rely on costly online interactions with real users, or rely on potentially…

cs.LG2020

Handling Variable-Dimensional Time Series with Graph Neural Networks

Vibhor Gupta, Jyoti Narwariya, Pankaj Malhotra +2

Several applications of Internet of Things (IoT) technology involve capturing data from multiple sensors resulting in multi-sensor time series. Existing neural networks based appro…