no code implementations • ICML 2020 • Abhimanyu Dubey, Alex `Sandy' Pentland
We study the heavy-tailed stochastic bandit problem in the cooperative multiagent setting, where a group of agents interact with a common bandit problem, while communicating on a network with delays.
no code implementations • ICML 2020 • Abhimanyu Dubey, Alex `Sandy' Pentland
We propose Coop-KernelUCB that provides near-optimal bounds on the per-agent regret in this setting, and is both computationally and communicatively efficient.
no code implementations • 6 Dec 2023 • Ivona Najdenkoska, Animesh Sinha, Abhimanyu Dubey, Dhruv Mahajan, Vignesh Ramanathan, Filip Radenovic
We propose Context Diffusion, a diffusion-based framework that enables image generation models to learn from visual examples presented in context.
no code implementations • 27 Sep 2023 • Xiaoliang Dai, Ji Hou, Chih-Yao Ma, Sam Tsai, Jialiang Wang, Rui Wang, Peizhao Zhang, Simon Vandenhende, Xiaofang Wang, Abhimanyu Dubey, Matthew Yu, Abhishek Kadian, Filip Radenovic, Dhruv Mahajan, Kunpeng Li, Yue Zhao, Vladan Petrovic, Mitesh Kumar Singh, Simran Motwani, Yi Wen, Yiwen Song, Roshan Sumbaly, Vignesh Ramanathan, Zijian He, Peter Vajda, Devi Parikh
Training text-to-image models with web scale image-text pairs enables the generation of a wide range of visual concepts from text.
1 code implementation • CVPR 2023 • Filip Radenovic, Abhimanyu Dubey, Abhishek Kadian, Todor Mihaylov, Simon Vandenhende, Yash Patel, Yi Wen, Vignesh Ramanathan, Dhruv Mahajan
Vision-language models trained with contrastive learning on large-scale noisy data are becoming increasingly popular for zero-shot recognition problems.
1 code implementation • CVPR 2023 • Vignesh Ramanathan, Anmol Kalia, Vladan Petrovic, Yi Wen, Baixue Zheng, Baishan Guo, Rui Wang, Aaron Marquez, Rama Kovvuri, Abhishek Kadian, Amir Mousavi, Yiwen Song, Abhimanyu Dubey, Dhruv Mahajan
This motivates the need for large datasets which go beyond traditional object masks and provide richer annotations such as part masks and attributes.
1 code implementation • 27 May 2022 • Abhimanyu Dubey, Filip Radenovic, Dhruv Mahajan
We demonstrate by human subject evaluations that SPAMs are demonstrably more interpretable in practice, and are hence an effortless replacement for DNNs for creating interpretable and high-performance systems suitable for large-scale machine learning.
1 code implementation • 27 May 2022 • Filip Radenovic, Abhimanyu Dubey, Dhruv Mahajan
However, these models are typically black-box deep neural networks, explained post-hoc via methods with known faithfulness limitations.
no code implementations • 27 May 2022 • Abhimanyu Dubey, Alex Pentland
In this paper, we investigate the stochastic bandit problem under two settings - (a) when the agents wish to make their communication private with respect to the action sequence, and (b) when the agents can be byzantine, i. e., they provide (stochastically) incorrect information.
1 code implementation • 9 Dec 2021 • Xavier Thomas, Dhruv Mahajan, Alex Pentland, Abhimanyu Dubey
In this paper, we propose a domain-adaptive approach to this problem, which operates in two steps: (a) we cluster training data within a carefully chosen feature space to create pseudo-domains, and (b) using these pseudo-domains we learn a domain-adaptive classifier that makes predictions using information about both the input and the pseudo-domain it belongs to.
Ranked #16 on Domain Generalization on PACS
no code implementations • NeurIPS 2021 • Udari Madhushani, Abhimanyu Dubey, Naomi Ehrich Leonard, Alex Pentland
However, most research for this problem focuses exclusively on the setting with perfect communication, whereas in most real-world distributed settings, communication is often over stochastic networks, with arbitrary corruptions and delays.
no code implementations • 17 Aug 2021 • Ziv Epstein, Matthew Groh, Abhimanyu Dubey, Alex "Sandy" Pentland
How does the visual design of digital platforms impact user behavior and the resulting environment?
no code implementations • CVPR 2021 • Abhimanyu Dubey, Vignesh Ramanathan, Alex Pentland, Dhruv Mahajan
We show that the existing approaches either do not scale to this dataset or underperform compared to the simple baseline of training a model on the union of data from all training domains.
no code implementations • 8 Mar 2021 • Abhimanyu Dubey, Alex Pentland
Reinforcement learning in cooperative multi-agent settings has recently advanced significantly in its scope, with applications in cooperative estimation for advertising, dynamic treatment regimes, distributed control, and federated learning.
no code implementations • 24 Feb 2021 • Abhimanyu Dubey
In this paper, we consider the ubiquitous problem of gaussian process (GP) bandit optimization from the lens of privacy-preserving statistics.
1 code implementation • NeurIPS 2020 • Abhimanyu Dubey, Alex Pentland
The rapid proliferation of decentralized learning systems mandates the need for differentially-private cooperative learning.
no code implementations • 14 Aug 2020 • Abhimanyu Dubey, Alex Pentland
For this problem, we propose \textsc{Coop-KernelUCB}, an algorithm that provides near-optimal bounds on the per-agent regret, and is both computationally and communicatively efficient.
no code implementations • 14 Aug 2020 • Abhimanyu Dubey, Alex Pentland
We study the heavy-tailed stochastic bandit problem in the cooperative multi-agent setting, where a group of agents interact with a common bandit problem, while communicating on a network with delays.
no code implementations • 29 Aug 2019 • Mayank Sharma, Suraj Tripathi, Abhimanyu Dubey, Jayadeva, Sai Guruju, Nihal Goalla
Reducing network complexity has been a major research focus in recent years with the advent of mobile technology.
no code implementations • 8 Jul 2019 • Abhimanyu Dubey, Alex Pentland
Thompson Sampling provides an efficient technique to introduce prior knowledge in the multi-armed bandit problem, along with providing remarkable empirical performance.
no code implementations • CVPR 2019 • Abhimanyu Dubey, Laurens van der Maaten, Zeki Yalniz, Yixuan Li, Dhruv Mahajan
Empirical evaluations of this defense strategy on ImageNet suggest that it is very effective in attack settings in which the adversary does not have access to the image database.
no code implementations • 16 Feb 2019 • Dhaval Adjodah, Dan Calacci, Abhimanyu Dubey, Anirudh Goyal, Peter Krafft, Esteban Moro, Alex Pentland
A common technique to improve learning performance in deep reinforcement learning (DRL) and many other machine learning algorithms is to run multiple learning agents in parallel.
1 code implementation • 27 Dec 2018 • Shayne O'Brien, Matt Groh, Abhimanyu Dubey
The true distribution parameterizations of commonly used image datasets are inaccessible.
no code implementations • 8 Dec 2018 • Praneeth Vepakomma, Tristan Swedish, Ramesh Raskar, Otkrist Gupta, Abhimanyu Dubey
We survey distributed deep learning models for training or inference without accessing raw data from clients.
no code implementations • NeurIPS 2018 • Abhimanyu Dubey, Otkrist Gupta, Ramesh Raskar, Nikhil Naik
Fine-Grained Visual Classification (FGVC) is an important computer vision problem that involves small diversity within the different classes, and often requires expert annotators to collect data.
Ranked #20 on Fine-Grained Image Classification on NABirds (using extra training data)
no code implementations • 30 Nov 2018 • Dhaval Adjodah, Dan Calacci, Abhimanyu Dubey, Peter Krafft, Esteban Moro, Alex `Sandy' Pentland
This is an important problem because a common technique to improve speed and robustness of learning in deep reinforcement learning and many other machine learning algorithms is to run multiple learning agents in parallel.
no code implementations • 16 Sep 2018 • Abhimanyu Dubey, Otkrist Gupta, Ramesh Raskar, Nikhil Naik
Fine-Grained Visual Classification (FGVC) is an important computer vision problem that involves small diversity within the different classes, and often requires expert annotators to collect data.
no code implementations • ECCV 2018 • Abhimanyu Dubey, Moitreya Chatterjee, Narendra Ahuja
We propose a novel Convolutional Neural Network (CNN) compression algorithm based on coreset representations of filters.
no code implementations • 20 Mar 2018 • Ziv Epstein, Blakeley H. Payne, Judy Hanwen Shen, Abhimanyu Dubey, Bjarke Felbo, Matthew Groh, Nick Obradovich, Manuel Cebrian, Iyad Rahwan
AI researchers employ not only the scientific method, but also methodology from mathematics and engineering.
no code implementations • 14 Feb 2018 • Abhimanyu Dubey, Esteban Moro, Manuel Cebrian, Iyad Rahwan
The analysis of the creation, mutation, and propagation of social media content on the Internet is an essential problem in computational social science, affecting areas ranging from marketing to political mobilization.
no code implementations • 22 Sep 2017 • Abhimanyu Dubey, Sumeet Agarwal
The study of virality and information diffusion online is a topic gaining traction rapidly in the computational social sciences.
no code implementations • 31 Jul 2017 • Jayadeva, Himanshu Pant, Mayank Sharma, Abhimanyu Dubey, Sumit Soman, Suraj Tripathi, Sai Guruju, Nihal Goalla
Our proposed approach yields benefits across a wide range of architectures, in comparison to and in conjunction with methods such as Dropout and Batch Normalization, and our results strongly suggest that deep learning techniques can benefit from model complexity control methods such as the LCNN learning rule.
1 code implementation • ECCV 2018 • Abhimanyu Dubey, Otkrist Gupta, Pei Guo, Ramesh Raskar, Ryan Farrell, Nikhil Naik
Fine-Grained Visual Classification (FGVC) datasets contain small sample sizes, along with significant intra-class variation and inter-class similarity.
Ranked #17 on Fine-Grained Image Classification on Stanford Dogs
no code implementations • 12 Sep 2016 • Abhimanyu Dubey, Jayadeva, Sumeet Agarwal
We compare several ConvNets with different depth and regularization techniques with multi-unit macaque IT cortex recordings and assess the impact of the same on representational similarity with the primate visual cortex.
1 code implementation • 5 Aug 2016 • Abhimanyu Dubey, Nikhil Naik, Devi Parikh, Ramesh Raskar, César A. Hidalgo
Computer vision methods that quantify the perception of urban environment are increasingly being used to study the relationship between a city's physical appearance and the behavior and health of its residents.
no code implementations • 19 Nov 2015 • Abhimanyu Dubey, Nikhil Naik, Dan Raviv, Rahul Sukthankar, Ramesh Raskar
We propose a method for learning from streaming visual data using a compact, constant size representation of all the data that was seen until a given moment.