Unpublished Manuscripts

Are Models Trained on Indian Legal Data Fair?

2023 SAIL 2023 View Article

Multi-Tailed, Multi-Headed, Spatial Dynamic Memory refined Text-to-Image Synthesis

2021 View Article

Using AI to Improve Maternal and Child Health Outcomes by Increasing Program Engagement through Targeted Interventions

2021 Accepted as a poster presentation at the Workshop on AI For Behavior Change in AAAI 2021.

RePReL: Integrating Relational Planning and Reinforcement Learning for Effective Abstraction

2021 Accepted as a poster presentation at the Planning and Reinforcement Learning (PRL) Workshop at ICAPS 2021.

Interactive Media for Understanding ML Methods: A Case-Study on Graph Neural Networks

2021 In Beyond static papers: Rethinking how we share scientific understanding in ML-ICLR 2021 workshop.

Using Reinforcement Learning for a Large Variable-Dimensional Inventory Management Problem

2020 Accepted as a poster presentation at Adaptive and Learning Agents (ALA) Workshop at AAMAS 2020, Auckland, New Zealand.

Reinforcement Learning for Improving Object Detection

2020 Accepted at the Second ECCV Real World Computer Vision from Inputs with Limited Quality (RLQ) Workshop. To appear in the ECCV 2020 Workshop Proceedings.

Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learning

2020 Accepted as a poster presentation at Adaptive and Learning Agents (ALA) Workshop at AAMAS 2020, Auckland, New Zealand.

On Incorporating Structural Information to improve Dialogue Response Generation

2020 To appear in the proceedings of the ACL NLPConvAI Workshop 2020.

Missed calls, Automated Calls and Health Support: Using AI to improve maternal health outcomes by increasing program engagement

2020 Presented at AI for Social Good - Harvard CRCS Workshop.

ERLP: Ensembles of Reinforcement Learning Policies

2020 In the Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI 2020) (Students ).

A Causal Linear Model to Quantify Edge Unfairness for Unfair Edge Prioritization and Discrimination Removal

2020 Accepted as a poster presentation at Law and Machine Learning (LML) Workshop at ICML 2020.

SEERL : Sample Efficient Ensemble Reinforcement Learning

2019 Accepted as a poster presentation at the Deep Reinforcement Learning workshop in NeurIPS 2019.

Polyphonic Music Composition with LSTM Neural Networks and Reinforcement Learning

2019 View Article

Optimal Resampling for Learning Small Models

2019 View Article

Network Representation Learning: Consolidation and Renewed Bearing

2019 View Article

Network discovery using Reinforcement Learning

2019 Accepted as a poster presentation at the Graph Representation Learning workshop in NeurIPS 2019. View Article

Learning policies for Social network discovery with Reinforcement learning

2019 View Article

Learning Interpretable Models Using an Oracle

2019 View Article

Hypergraph Partitioning using Tensor Eigenvalue Decomposition

2019 Accepted as a poster presentation at the Sets & Partitions workshop in NeurIPS 2019.

Hyperedge Prediction using Tensor Eigenvalue Decomposition

2019 Accepted as a poster presentation at the Tensor Methods for Emerging Data Science Challenges (TMEDSC) workshop in KDD 2019.

ExTra: Transfer-guided Exploration

2019 Accepted as a poster presentation at the Montreal AI Symposium. Montreal, Canada. View Article

An active learning framework for efficient robust policy search

2019 Accepted as a poster presentation at the Safety and Robustness in Decision Making workshop in NeurIPS 2019. View Article

Hypergraph Clustering: A Modularity Maximization Approach

2018 View Article

HOPF: Higher Order Propagation Framework for Deep Collective Classification

2018 Presented at the Eighth International Workshop on Statistical Relational AI at the 27th International Joint Conference on Artificial Intelligence (IJCAI 2018). View Article

Fusion Graph Convolutional Networks

2018 Presented at the 14th International Workshop on Machine Learning with Graphs, 24th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2018). (Expanded version of NIPS 2016 workshop paper) View Article

Discovering hierarchies using Imitation Learning from hierarchy aware policies

2018 View Article

DiGrad: Multi-Task Reinforcement Learning with Shared Actions

2018 View Article

Shared Learning : Enhancing Reinforcement in Q-Ensembles

2017 View Article

Rate of Change Analysis for Interestingness Measures

2017 View Article

Prediction Error-based Transfer in Q-Ensembles

2017 Accepted at the 2017 NIPS Deep Reinforcement Learning Symposium. View Article

Online Multi-Task Learning Using Active Sampling

2017 Accepted at the Fifth International Conference on Learning Representations (ICLR 2017) Workshop Track.

MCEIL: An Improved Scoring Function for Overlapping Community Detection using Seed Expansion Methods

2017 Presented at the Sixth International Workshop on Social Networks Analytics in Applications (SNAA 2017) held with the Ninth IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2017), Sydney, Australia.

Learning to Multi-Task by Active Sampling

2017 (Expanded version of the ICLR 2017 workshop paper) View Article

Learning to Mix n-Step Returns: Generalizing lambda-Returns for Deep Reinforcement Learning

2017 View Article

Learning to Factor Policies and Action-Value Functions: Factored Action Space Representations for Deep Reinforcement learning

2017 View Article

DyVEDeep: Dynamic Variable Effort Deep Neural Networks

2017 View Article

SLAM-Safe Planner: Preventing Monocular SLAM Failure using Reinforcement Learning

2016 View Article

Linear Bandit algorithms using the Bootstrap

2016 Expanded version of the RLDM poster below. View Article

Language Expansion In Text-Based Games

2016 Accepted at the 2016 NIPS workshop on Deep Reinforcement Learning. View Article

Imitation Learning by Programs

2016 Accepted at the 2016 NIPS workshop on Deep Reinforcement Learning. View Article

Hierarchical Reinforcement Learning using Spatio-Temporal Abstractions and Deep Neural Networks

2016 Accepted at the ICML Workshop on ion in Reinforcement Learning, New York City, June 2016. version. View Article

Exploration for Multi-task Reinforcement Learning with Deep Generative Models

2016 Accepted at the 2016 NIPS workshop on Deep Reinforcement Learning. View Article

Dynamic Frame skip Deep Q Network

2016 Accepted at the IJCAI Workshop on Deep Reinforcement Learning: Frontiers and Challenges, New Yok City, July 2016. version. View Article

A Developmental Approach to Learning Affordances

2016 Accepted at the 2016 NIPS workshop on Continual Learning and Deep Learning. View Article

TSEB: More Efficient Thompson Sampling for Policy Learning

2015 Expanded version of he RLDM poster below. View Article

Thompson Sampling with Adaptive Exploration Bonus for Near-Optimal Policy Learning

2015 Accepted at the 2nd Multidisciplinary Conference on Reinforcement Learning and Decision Making, Alberta, Canada, June 2015.

Scalable Bayesian Matrix Factorization

2015 Accepted at the Sixth International Workshop on Mining Ubiquitous and Social Environments (MUSE), co-located with ECML/PKDD 2015, Porto, Portugal.

KWIK Inverse Reinforcement Learning

2015 Accepted at the 2nd Multidisciplinary Conference on Reinforcement Learning and Decision Making, Alberta, Canada, June 2015.

Hierarchical Decision Making using Spatio-Temporal Abstractions In Reinforcement Learning

2015 Accepted at the 2nd Multidisciplinary Conference on Reinforcement Learning and Decision Making, Alberta, Canada, June 2015.

Bootstrapped Linear Bandits

2015 Accepted at the 2nd Multidisciplinary Conference on Reinforcement Learning and Decision Making, Alberta, Canada, June 2015.

ADAAPT: A Deep Architecture for Adaptive Policy Transfer from Multiple Sources

2015 View Article

A Reinforcement Learning Approach to Online Learning of Decision Trees

2015 Accepted at the European Workshop on Reinforcement Learning (EWRL 2015). View Article

A Computational Model of Gait Changes in Parkinson’s Disease Patients Passing Through Doorways

2015 Accepted at the 2nd Multidisciplinary Conference on Reinforcement Learning and Decision Making, Alberta, Canada, June 2015.

Targeted Influence Maximization through a Social Network

2014 Presented at the NIPS workshop on Networks: From Graphs to Rich Data. View Article

Scalable Positional Analysis for Studying Evolution of Nodes in Networks

2014 Accepted for presentation in the Workshop on Mining Networks and Graphs, at the Siam Conference on Data Mining (SDM 14). View Article

iBayes: A Thompson Sampling Approach to Reinforcement Learning with Instructions

2014 Presented at the NIPS workshop on Novel Trends and Applications in Reinforcement Learning.

Studying Indian Railways Network using Hypergraphs

2013 Accepted as a poster presentation at the International School and Conference on Network Science (NetSci 2013). Copenhagen, Denmark.

Spectral Clustering as Mapping to a Simplex

2013 Accepted at the 2013 ICML workshop on Spectral Learning. Atlanta, GA, USA.

Multilingual Deep Learning

2013 In the Deep Learning Workshop at NIPS 2013.

Why Collective Classification is Successful? : A Homophily based Analysis on Network Data

2012 Accepted for presentation at the Thirty Second Sunbelt Social Networks Conference (Sunbelt XXXII).

Multiple Epsilon Equitable Partitions - Roles and Positional Analysis for Real World Networks

2012 Accepted for presentation at the Thirty Second Sunbelt Social Networks Conference (Sunbelt XXXII).

Integrating Human Instructions and Reinforcement Learners : An SRL Approach

2012 In the Proceedings of the UAI workshop on Statistical Relational AI (StarAI 2012).

Discovering Continuous Homomorphisms for Transfer

2012 In the Proceedings of the European Workshop on Reinforcement Learning (EWRL 2012).

Abstraction in Reinforcement Learning in Terms of Metastability

2012 In the Proceedings of the European Workshop on Reinforcement Learning (EWRL 2012).

Collective Learning of the Community Effect on Chrun

2011 Accepted at the Workshop on Collective Learning and Inference on Structured Data, held in conjunction with the Twenty Second European Conference on Machine Learning (ECML PKDD 2011).

Beyond Rewards: Learning with Richer Supervision

2011 In the Proceedings of the Ninth European Workshop on Reinforcement Learning (EWRL 2011).

The Role of Basal Ganglia in Performing Simple Reaching Movements: A Computational Model

2009 Presented at the Multidisciplinary Symposium on Reinforcement Learning. (Shorter version of the paper at IGS09.)

Personalized Intelligent Tutoring System Using Reinforcement Learning

2009 Presented at the Multidisciplinary Symposium on Reinforcement Learning. (Preliminary version of the paper at FLAIRS 2011.)

Transfer Learning with Differently-abled Robots

2008 In the IROS Workshop on Robotics Challenges for Machine Learning.

Detection of keratoconus by semi-supervised learning

2008 In the ICML/UAI workshop on Machine Learning in health care applications. View Article

Document Clustering using Lexical Chains

2007 In the Proceedings of the Workshop on Text-Mining & Link-Analysis (TextLink 2007). View Article

Part Of Speech Tagging and Chunking with HMM and CRF

2006 In the Proceedings of NLPAI Machine Learning Contest 2006 , Mumbai, India.

Learn to Teach Autistic Children

2005 Presented in the National Conference on Computational Intelligence (St. Joseph’s College, Trichy), Feb 16-18.

A Review of Automatic Summarization

2005 Presented in the Workshop on Optical character Recognition with workflow and Document Summarization, IIIT Allahabad, March 19-20.