Search Results for author: Abhishek Sinha

Found 33 papers, 9 papers with code

Confidence Is All You Need for MI Attacks

no code implementations26 Nov 2023 Abhishek Sinha, Himanshi Tibrewal, Mansi Gupta, Nikhar Waghela, Shivank Garg

In this attack, adversaries aim to determine whether a particular point was used during the training of a target model.

Playing in the Dark: No-regret Learning with Adversarial Constraints

no code implementations29 Oct 2023 Abhishek Sinha, Rahul Vaze

This is achieved via a black box reduction of the constrained problem to the standard OCO problem for a recursively constructed sequence of surrogate cost functions.

Multi-Task Learning

$α$-Fair Contextual Bandits

no code implementations22 Oct 2023 Siddhant Chaudhary, Abhishek Sinha

In this paper, we consider the $\alpha$-Fair Contextual Bandits problem, where the objective is to maximize the global $\alpha$-fair utility function - a non-decreasing concave function of the cumulative rewards in the adversarial setting.

Multi-Armed Bandits Recommendation Systems

$\texttt{BanditQ}:$ Fair Multi-Armed Bandits with Guaranteed Rewards per Arm

no code implementations11 Apr 2023 Abhishek Sinha

In this paper, we consider a fair prediction problem in the stochastic setting with hard lower bounds on the rate of accrual of rewards for a set of arms.

Multi-Armed Bandits

Online Subset Selection using $α$-Core with no Augmented Regret

no code implementations28 Sep 2022 Sourav Sahoo, Siddhant Chaudhary, Samrat Mukhopadhyay, Abhishek Sinha

In this connection, we propose an online learning policy called SCore (Subset Selection with Core) that solves the problem for a large class of reward functions.

Optimistic No-regret Algorithms for Discrete Caching

no code implementations15 Aug 2022 Naram Mhaisen, Abhishek Sinha, Georgios Paschos, Georgios Iosifidis

We take a systematic look at the problem of storing whole files in a cache with limited capacity in the context of optimistic learning, where the caching policy has access to a prediction oracle (provided by, e. g., a Neural Network).

Universal Caching

1 code implementation10 May 2022 Ativ Joshi, Abhishek Sinha

In learning theory, the performance of an online policy is commonly measured in terms of the static regret metric, which compares the cumulative loss of an online policy to that of an optimal benchmark in hindsight.

Learning Theory

$\texttt{LeadCache}$: Regret-Optimal Caching in Networks

no code implementations NeurIPS 2021 Debjit Paria, Abhishek Sinha

We show that $\texttt{LeadCache}$ is regret-optimal up to a factor of $\tilde{O}(n^{3/8}),$ where $n$ is the number of users.

D2C: Diffusion-Decoding Models for Few-Shot Conditional Generation

1 code implementation NeurIPS 2021 Abhishek Sinha, Jiaming Song, Chenlin Meng, Stefano Ermon

Conditional generative models of high-dimensional images have many applications, but supervision signals from conditions to images can be expensive to acquire.

Conditional Image Generation Image Manipulation +1

$k\texttt{-experts}$ -- Online Policies and Fundamental Limits

no code implementations15 Oct 2021 Samrat Mukhopadhyay, Sourav Sahoo, Abhishek Sinha

Unlike the classic version, where the learner selects exactly one expert from a pool of $N$ experts at each round, in this problem, the learner can select a subset of $k$ experts at each round $(1\leq k\leq N)$.

D2C: Diffusion-Denoising Models for Few-shot Conditional Generation

2 code implementations12 Jun 2021 Abhishek Sinha, Jiaming Song, Chenlin Meng, Stefano Ermon

Conditional generative models of high-dimensional images have many applications, but supervision signals from conditions to images can be expensive to acquire.

Conditional Image Generation Denoising +2

Hybrid Mutual Information Lower-bound Estimators for Representation Learning

no code implementations ICLR Workshop Neural_Compression 2021 Abhishek Sinha, Jiaming Song, Stefano Ermon

We illustrate that with one set of representations, the hybrid approach is able to achieve good performance on multiple downstream tasks such as classification, reconstruction, and generation.

Representation Learning

Negative Data Augmentation

2 code implementations ICLR 2021 Abhishek Sinha, Kumar Ayush, Jiaming Song, Burak Uzkent, Hongxia Jin, Stefano Ermon

Empirically, models trained with our method achieve improved conditional/unconditional image generation along with improved anomaly detection capabilities.

Action Recognition Anomaly Detection +9

Online Caching with Optimal Switching Regret

no code implementations18 Jan 2021 Samrat Mukhopadhyay, Abhishek Sinha

The objective is to design a caching policy that incurs minimal regret while considering both the rewards due to cache-hits and the switching cost due to the file fetches.

H-divergence: A Decision-Theoretic Discrepancy Measure for Two Sample Tests

no code implementations1 Jan 2021 Shengjia Zhao, Abhishek Sinha, Yutong He, Aidan Perreault, Jiaming Song, Stefano Ermon

Based on ideas from decision theory, we investigate a new class of discrepancies that are based on the optimal decision loss.

Vocal Bursts Valence Prediction

LeadCache: Regret-Optimal Caching in Networks

1 code implementation17 Sep 2020 Debjit Paria, Abhishek Sinha

We show that $\texttt{LeadCache}$ is regret-optimal up to a factor of $\tilde{O}(n^{3/8}),$ where $n$ is the number of users.

Combinatorial Optimization

On the Benefits of Models with Perceptually-Aligned Gradients

no code implementations4 May 2020 Gunjan Aggarwal, Abhishek Sinha, Nupur Kumari, Mayank Singh

In this paper, we leverage models with interpretable perceptually-aligned features and show that adversarial training with low max-perturbation bound can improve the performance of models for zero-shot and weakly supervised localization tasks.

cFineGAN: Unsupervised multi-conditional fine-grained image generation

no code implementations6 Dec 2019 Gunjan Aggarwal, Abhishek Sinha

We propose an unsupervised multi-conditional image generation pipeline: cFineGAN, that can generate an image conditioned on two input images such that the generated image preserves the texture of one and the shape of the other input.

Conditional Image Generation

A Method for Computing Class-wise Universal Adversarial Perturbations

no code implementations1 Dec 2019 Tejus Gupta, Abhishek Sinha, Nupur Kumari, Mayank Singh, Balaji Krishnamurthy

We present an algorithm for computing class-specific universal adversarial perturbations for deep neural networks.

Intrusion Detection using Sequential Hybrid Model

no code implementations26 Oct 2019 Aditya Pandey, Abhishek Sinha, Aishwarya PS

A large amount of work has been done on the KDD 99 dataset, most of which includes the use of a hybrid anomaly and misuse detection model done in parallel with each other.

Anomaly Detection Network Intrusion Detection

Harnessing the Vulnerability of Latent Layers in Adversarially Trained Models

1 code implementation13 May 2019 Mayank Singh, Abhishek Sinha, Nupur Kumari, Harshitha Machiraju, Balaji Krishnamurthy, Vineeth N. Balasubramanian

We analyze the adversarially trained robust models to study their vulnerability against adversarial attacks at the level of the latent layers.

Adversarial Attack

Attention Based Natural Language Grounding by Navigating Virtual Environment

1 code implementation23 Apr 2018 Akilesh B, Abhishek Sinha, Mausoom Sarkar, Balaji Krishnamurthy

We develop an attention mechanism for multi-modal fusion of visual and textual modalities that allows the agent to learn to complete the task and achieve language grounding.

Navigate Zero-shot Generalization

Neural Networks in Adversarial Setting and Ill-Conditioned Weight Space

no code implementations3 Jan 2018 Mayank Singh, Abhishek Sinha, Balaji Krishnamurthy

Recently, Neural networks have seen a huge surge in its adoption due to their ability to provide high accuracy on various tasks.

Learning to navigate by distilling visual information and natural language instructions

no code implementations ICLR 2018 Abhishek Sinha, Akilesh B, Mausoom Sarkar, Balaji Krishnamurthy

In this work, we focus on the problem of grounding language by training an agent to follow a set of natural language instructions and navigate to a target object in a 2D grid environment.

Navigate Zero-shot Generalization

Intelligent Fault Analysis in Electrical Power Grids

no code implementations8 Nov 2017 Biswarup Bhattacharya, Abhishek Sinha

Power grids are one of the most important components of infrastructure in today's world.

Deep Fault Analysis and Subset Selection in Solar Power Grids

no code implementations8 Nov 2017 Biswarup Bhattacharya, Abhishek Sinha

Non-availability of reliable and sustainable electric power is a major problem in the developing world.

Intelligent Subset Selection of Power Generators for Economic Dispatch

no code implementations8 Sep 2017 Biswarup Bhattacharya, Abhishek Sinha

Sustainable and economical generation of electrical power is an essential and mandatory component of infrastructure in today's world.

Introspection: Accelerating Neural Network Training By Learning Weight Evolution

no code implementations17 Apr 2017 Abhishek Sinha, Mausoom Sarkar, Aahitagni Mukherjee, Balaji Krishnamurthy

In this paper, we explore the idea of learning weight evolution pattern from a simple network for accelerating training of novel neural networks.

General Classification

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