Sarath Chandar

发表

Multilingual Deep Learning

Sarath Chandar, 2013 .

Toward Training Recurrent Neural Networks for Lifelong Learning

Yoshua Bengio, Shagun Sodhani, Sarath Chandar, 2018, Neural Computation.

Lifelong Learning : A Reinforcement Learning Approach

Shie Mannor, Balaraman Ravindran, D. Mankowitz, 2022 .

Workshop on Machine Learning for Autonomous Vehicles 2017

Silvio Savarese, Balaraman Ravindran, Raquel Urtasun, .

Correlational Neural Networks for Common Representation Learning

Balaraman Ravindran, Balaraman Ravindran, Sarath Chandar, 2015 .

SUPPLEMENTARY MATERIAL-LEARNING TO NAVIGATE THE SYNTHETICALLY ACCESSIBLE CHEMICAL SPACE USING REINFORCEMENT LEARNING

Connor W. Coley, Sai Krishna Gottipati, Shengchao Liu, 2020 .

Chaotic Continual Learning

I. Rish, Sarath Chandar, Touraj Laleh, 2020 .

The Octopus Approach to the Alexa Competition : A Deep Ensemble-based Socialbot

Nan Rosemary Ke, Yoshua Bengio, A. D. Brébisson, 2017 .

Out-of-Distribution Classification and Clustering

Gabriele Prato, Sarath Chandar, Sarath Chandar, 2020 .

Improving Meta-Learning Generalization with Activation-Based Early-Stopping

Sarath Chandar, Gonçalo Mordido, C. Pal, 2022, CoLLAs.

Segmentation of Multiple Sclerosis Lesions across Hospitals: Learn Continually or Train from Scratch?

D. Reich, Sarath Chandar, M. Filippi, 2022, 2210.15091.

Local Structure Matters Most in Most Languages

Sarath Chandar, A. Zouaq, Prasanna Parthasarathi, 2022, AACL.

Sharpness-Aware Training for Accurate Inference on Noisy DNN Accelerators

Sarath Chandar, Gonçalo Mordido, Franccois Leduc-Primeau, 2022, ArXiv.

Memory Augmented Optimizers for Deep Learning pdf

Mahmoud Assran, Sarath Chandar, Paul-Aymeric McRae, 2021, ICLR.

Local Structure Matters Most: Perturbation Study in NLU

Sarath Chandar, A. Zouaq, Prasanna Parthasarathi, 2021, FINDINGS.

A Survey of Data Augmentation Approaches for NLP pdf

Eduard Hovy, Teruko Mitamura, Soroush Vosoughi, 2021, FINDINGS.

Demystifying Neural Language Models' Insensitivity to Word-Order pdf

Amal Zouaq, Sarath Chandar, Prasanna Parthasarathi, 2021, ArXiv.

Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning pdf

Yoshua Bengio, Sufeng Niu, Yashaswi Pathak, 2020, ICML.

Continuous Coordination As a Realistic Scenario for Lifelong Learning

Aaron C. Courville, Sarath Chandar, Hadi Nekoei, 2021, ICML.

UOUS AND DISCRETE ADDRESSING SCHEMES

Yoshua Bengio, Kyunghyun Cho, Sarath Chandar, 2016 .

Deep Learning on a Healthy Data Diet: Finding Important Examples for Fairness

Sarath Chandar, H. Palangi, Gonçalo Mordido, 2022, AAAI.

An Empirical Investigation of the Role of Pre-training in Lifelong Learning pdf

Sanket Vaibhav Mehta, Emma Strubell, Sarath Chandar, 2021, ArXiv.

Dealing With Non-stationarity in Decentralized Cooperative Multi-Agent Deep Reinforcement Learning via Multi-Timescale Learning

Aditya Mahajan, Sarath Chandar, Amit Sinha, 2023, ArXiv.

PatchBlender: A Motion Prior for Video Transformers

R. Devon Hjelm, Neel Joshi, Sarath Chandar, 2022, ArXiv.

Scaling Laws for the Few-Shot Adaptation of Pre-trained Image Classifiers pdf

Ethan Caballero, Irina Rish, Gabriele Prato, 2021, ArXiv.

Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement Learning

Yangchen Pan, Sarath Chandar, Chenjun Xiao, 2023, ArXiv.

SAMSON: Sharpness-Aware Minimization Scaled by Outlier Normalization for Improving DNN Generalization and Robustness

Sarath Chandar, Gonçalo Mordido, Sébastien Henwood, 2022, 2211.11561.

Thompson sampling for improved exploration in GFlowNets

Y. Bengio, Sarath Chandar, Kanika Madan, 2023, ArXiv.

Maximum Reward Formulation In Reinforcement Learning pdf

Matthew E. Taylor, Yashaswi Pathak, Sriram Ganapathi Subramanian, 2020, ArXiv.

How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics pdf

Joelle Pineau, Sarath Chandar, Prasanna Parthasarathi, 2020, ArXiv.

TAG: T ASK - BASED A CCUMULATED G RADIENTS FOR L IFELONG LEARNING

Sarath Chandar, B. Ravindran, Pranshu Malviya, 2022 .

Should We Attend More or Less? Modulating Attention for Fairness

Sarath Chandar, Gonçalo Mordido, S. Shabanian, 2023, ArXiv.

Promoting Exploration in Memory-Augmented Adam using Critical Momenta

Reza Babanezhad Harikandeh, Razvan Pascanu, S. Lacoste-Julien, 2023, arXiv.org.

MLMLM: Link Prediction with Mean Likelihood Masked Language Model pdf

Amal Zouaq, A. P. Sarath Chandar, Louis Clouâtre, 2020, FINDINGS.

Slot Contrastive Networks: A Contrastive Approach for Representing Objects pdf

A. P. Sarath Chandar, Evan Racah, A. Chandar, 2020, ArXiv.

MAXIMUM REWARD FORMULATION IN REINFORCE-

Sriram Ganapathi Subramanian, Sai Krishna Gottipati, Sahir, 2020 .

Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods

H. V. Seijen, I. Momennejad, A. Chandar, 2022, ICML.

An Empirical Investigation of the Role of Pre-training in Lifelong Learning

Sanket Vaibhav Mehta, Sarath Chandar, Emma Strubell, 2021, J. Mach. Learn. Res..

Lookbehind Optimizer: k steps back, 1 step forward

A. Baratin, Sarath Chandar, Gonçalo Mordido, 2023, ArXiv.

Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement Learning

Yangchen Pan, Sarath Chandar, Chenjun Xiao, 2023, UAI.

TAG: Task-based Accumulated Gradients for Lifelong learning

A. Chandar, Sarath Chandar, B. Ravindran, 2021, CoLLAs.

Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In the Game of Hanabi

Miao Liu, Sarath Chandar, Janarthanan Rajendran, 2023, ArXiv.

Improving Sample Efficiency of Value Based Models Using Attention and Vision Transformers

Doina Precup, Sarath Chandar, Mohammad Amini, 2022, ArXiv.

Detecting Languages Unintelligible to Multilingual Models through Local Structure Probes

Sarath Chandar, A. Zouaq, Prasanna Parthasarathi, 2022, EMNLP.

Toward Training Recurrent Neural Networks for Lifelong Learning

Yoshua Bengio, Shagun Sodhani, Sarath Chandar, 2019, Neural Computation.

Faithfulness Measurable Masked Language Models

Sarath Chandar, Siva Reddy, Andreas Madsen, 2023, ArXiv.

Replay Buffer with Local Forgetting for Adapting to Local Environment Changes in Deep Model-Based Reinforcement Learning

H. V. Seijen, I. Momennejad, Sarath Chandar, 2023, CoLLAs.

Are self-explanations from Large Language Models faithful?

Sarath Chandar, Siva Reddy, Andreas Madsen, 2024, ArXiv.

EpiK-Eval: Evaluation for Language Models as Epistemic Models

Shagun Sodhani, Sarath Chandar, Gabriele Prato, 2023, Conference on Empirical Methods in Natural Language Processing.

Measuring the Knowledge Acquisition-Utilization Gap in Pretrained Language Models

Sarath Chandar, Prasanna Parthasarathi, Mehdi Rezagholizadeh, 2023, EMNLP.

Dealing With Non-stationarity in Decentralized Cooperative Multi-Agent Deep Reinforcement Learning via Multi-Timescale Learning

Aditya Mahajan, Sarath Chandar, Amit Sinha, 2023, CoLLAs.

Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement Learning

Yangchen Pan, Sarath Chandar, Chenjun Xiao, 2023, UAI.

Fairness-Aware Structured Pruning in Transformers

Sarath Chandar, S. Shabanian, A. Zayed, 2023, AAAI.

Mastering Memory Tasks with World Models

Mohammad Reza Samsami, Sarath Chandar, Artem Zholus, 2024, ArXiv.

Memory Augmented Neural Networks for Natural Language Processing

Sarath Chandar, Caglar Gulcehre, Caglar Gulcehre, 2017, EMNLP.

On the Costs and Benefits of Adopting Lifelong Learning for Software Analytics - Empirical Study on Brown Build and Risk Prediction

Sarath Chandar, Mathieu Nayrolles, Mojtaba Faramarzi, 2023, 2024 IEEE/ACM 46th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP).

Replay Buffer With Local Forgetting for Adaptive Deep Model-Based Reinforcement Learning

H. V. Seijen, I. Momennejad, A. Chandar, 2023, ArXiv.

Predicting the Impact of Model Expansion through the Minima Manifold: A Loss Landscape Perspective

Sarath Chandar, Pranshu Malviya, Jerry Huang, 2024, ArXiv.