Search Results for author: Abhimanyu Dubey

Found 36 papers, 9 papers with code

Robust Multi-Agent Decision-Making with Heavy-Tailed Payoffs

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.

Decision Making

Kernel Methods for Cooperative Multi-Agent Learning 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.

Clustering Decision Making

Context Diffusion: In-Context Aware Image Generation

no code implementations6 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.

Image Generation In-Context Learning

Neural Basis Models for Interpretability

1 code implementation27 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.

Additive models Interpretable Machine Learning

Scalable Interpretability via Polynomials

1 code implementation27 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.

Additive models BIG-bench Machine Learning +1

Private and Byzantine-Proof Cooperative Decision-Making

no code implementations27 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.

Decision Making

Adaptive Methods for Aggregated Domain Generalization

1 code implementation9 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.

Domain Generalization

One More Step Towards Reality: Cooperative Bandits with Imperfect Communication

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.

Decision Making

Social influence leads to the formation of diverse local trends

no code implementations17 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?

Adaptive Methods for Real-World Domain Generalization

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.

Domain Generalization

Provably Efficient Cooperative Multi-Agent Reinforcement Learning with Function Approximation

no code implementations8 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.

Federated Learning Multi-agent Reinforcement Learning +2

No-Regret Algorithms for Private Gaussian Process Bandit Optimization

no code implementations24 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.

Decision Making Privacy Preserving

Differentially-Private Federated Linear Bandits

1 code implementation NeurIPS 2020 Abhimanyu Dubey, Alex Pentland

The rapid proliferation of decentralized learning systems mandates the need for differentially-private cooperative learning.

Federated Learning

Kernel Methods for Cooperative Multi-Agent Contextual Bandits

no code implementations14 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.

Decision Making Multi-Armed Bandits

Cooperative Multi-Agent Bandits with Heavy Tails

no code implementations14 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.

Smaller Models, Better Generalization

no code implementations29 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.

Quantization

Thompson Sampling on Symmetric $α$-Stable Bandits

no code implementations8 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.

Bayesian Inference Decision Making +2

Defense Against Adversarial Images using Web-Scale Nearest-Neighbor Search

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.

Leveraging Communication Topologies Between Learning Agents in Deep Reinforcement Learning

no code implementations16 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.

BIG-bench Machine Learning reinforcement-learning +1

Evaluating Generative Adversarial Networks on Explicitly Parameterized Distributions

1 code implementation27 Dec 2018 Shayne O'Brien, Matt Groh, Abhimanyu Dubey

The true distribution parameterizations of commonly used image datasets are inaccessible.

No Peek: A Survey of private distributed deep learning

no code implementations8 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.

Federated Learning

Maximum-Entropy Fine Grained Classification

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)

Classification Diversity +2

How to Organize your Deep Reinforcement Learning Agents: The Importance of Communication Topology

no code implementations30 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.

BIG-bench Machine Learning Reinforcement Learning (RL)

Maximum-Entropy Fine-Grained Classification

no code implementations16 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.

Classification Diversity +2

Coreset-Based Neural Network Compression

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.

Neural Network Compression Quantization

MemeSequencer: Sparse Matching for Embedding Image Macros

no code implementations14 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.

Clustering Image Clustering +3

Modeling Image Virality with Pairwise Spatial Transformer Networks

no code implementations22 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.

Attribute

Learning Neural Network Classifiers with Low Model Complexity

no code implementations31 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.

Examining Representational Similarity in ConvNets and the Primate Visual Cortex

no code implementations12 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.

Deep Learning the City : Quantifying Urban Perception At A Global Scale

1 code implementation5 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.

General Classification

Coreset-Based Adaptive Tracking

no code implementations19 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.

Object Object Tracking

Cannot find the paper you are looking for? You can Submit a new open access paper.