no code implementations • 1 Mar 2024 • Nishanth Chandran, Sunayana Sitaram, Divya Gupta, Rahul Sharma, Kashish Mittal, Manohar Swaminathan
To solve this problem, we propose Private Benchmarking, a solution where test datasets are kept private and models are evaluated without revealing the test data to the model.
no code implementations • 15 Feb 2024 • Kleanthis Avramidis, Melinda Y. Chang, Rahul Sharma, Mark S. Borchert, Shrikanth Narayanan
A wide range of neurological and cognitive disorders exhibit distinct behavioral markers aside from their clinical manifestations.
no code implementations • 16 Jan 2024 • Rahul Sharma, Sergey Redyuk, Sumantrak Mukherjee, Andrea Sipka, Sebastian Vollmer, David Selby
Explainable AI (XAI) and interpretable machine learning methods help to build trust in model predictions and derived insights, yet also present a perverse incentive for analysts to manipulate XAI metrics to support pre-specified conclusions.
no code implementations • 27 Nov 2023 • Gayan Lankeshwara, Rahul Sharma, M. R. Alam, Ruifeng Yan, Tapan K. Saha
In the second stage, the demand response aggregator (DRA) utilises DOEs assigned by the DNSP to develop a hierarchical control scheme for tracking a load set-point signal without jeopardising network statutory limits.
no code implementations • 14 Nov 2023 • Adharsh Kamath, Aditya Senthilnathan, Saikat Chakraborty, Pantazis Deligiannis, Shuvendu K. Lahiri, Akash Lal, Aseem Rastogi, Subhajit Roy, Rahul Sharma
Finally, we explore the effectiveness of using an efficient combination of a symbolic tool and an LLM on our dataset and compare it against a purely symbolic baseline.
no code implementations • 6 Nov 2023 • Minakshi Kaushik, Rahul Sharma, Dirk Draheim
We conduct an extensive analysis of human perceptions of partitioning a numerical attribute and compare these perceptions with the results obtained from our two proposed measures.
1 code implementation • 13 Oct 2023 • Saikat Chakraborty, Shuvendu K. Lahiri, Sarah Fakhoury, Madanlal Musuvathi, Akash Lal, Aseem Rastogi, Aditya Senthilnathan, Rahul Sharma, Nikhil Swamy
In this work, we observe that Large Language Models (such as gpt-3. 5 or gpt-4) are capable of synthesizing loop invariants for a class of programs in a 0-shot setting, yet require several samples to generate the correct invariants.
no code implementations • 2 Jul 2023 • Minakshi Kaushik, Rahul Sharma, Iztok Fister Jr., Dirk Draheim
Numerical association rule mining is a widely used variant of the association rule mining technique, and it has been extensively used in discovering patterns and relationships in numerical data.
no code implementations • 31 Jan 2023 • Wonyeol Lee, Rahul Sharma, Alex Aiken
Hence, it is important to use a precision assignment -- a mapping from all tensors (arising in training) to precision levels (high or low) -- that keeps most of the tensors in low precision and leads to sufficiently accurate models.
no code implementations • 16 Jan 2023 • Shradha Verma, Tripti Goel, M Tanveer, Weiping Ding, Rahul Sharma, R Murugan
Moreover, for accurate diagnosis of SCZ, researchers have used machine learning (ML) algorithms for the past decade to distinguish the brain patterns of healthy and SCZ brains using MRI and fMRI images.
1 code implementation • 1 Dec 2022 • Rahul Sharma, Shrikanth Narayanan
Active speaker detection in videos addresses associating a source face, visible in the video frames, with the underlying speech in the audio modality.
Ranked #1 on Audio-Visual Active Speaker Detection on VPCD
no code implementations • 29 Oct 2022 • Shikhar Jaiswal, Rahul Kiran Kranti Goli, Aayan Kumar, Vivek Seshadri, Rahul Sharma
Running machine learning inference on tiny devices, known as TinyML, is an emerging research area.
no code implementations • 28 Sep 2022 • Abhishek Dasgupta, Rahul Sharma, Challenger Mishra, Vikranth H. Nagaraja
Marker-based Optical Motion Capture (OMC) systems and associated musculoskeletal (MSK) modelling predictions offer non-invasively obtainable insights into in vivo joint and muscle loading, aiding clinical decision-making.
1 code implementation • 24 Sep 2022 • Rahul Sharma, Shrikanth Narayanan
We leverage speaker identity information from speech and faces, and formulate active speaker detection as a speech-face assignment task such that the active speaker's face and the underlying speech identify the same person (character).
no code implementations • 26 Aug 2022 • Vinod Ganesan, Anwesh Bhattacharya, Pratyush Kumar, Divya Gupta, Rahul Sharma, Nishanth Chandran
For instance, the model provider could be a diagnostics company that has trained a state-of-the-art DenseNet-121 model for interpreting a chest X-ray and the user could be a patient at a hospital.
no code implementations • NAACL 2022 • Rahul Sharma, Anil Ramakrishna, Ansel MacLaughlin, Anna Rumshisky, Jimit Majmudar, Clement Chung, Salman Avestimehr, Rahul Gupta
Federated learning (FL) has recently emerged as a method for training ML models on edge devices using sensitive user data and is seen as a way to mitigate concerns over data privacy.
no code implementations • 30 Mar 2022 • Rahul Sharma, Shrikanth Narayanan
Speaker diarization is one of the critical components of computational media intelligence as it enables a character-level analysis of story portrayals and media content understanding.
no code implementations • 21 Mar 2022 • Rahul Sharma, Shrikanth Narayanan
We curate a background character dataset which provides annotations for background character for a set of TV shows, and use it to evaluate the performance of the background character detection framework.
1 code implementation • 30 Sep 2021 • Rahul Sharma, Kunal Dhawan, Balakrishna Pailla
This work presents a novel methodology for calculating the phonetic similarity between words taking motivation from the human perception of sounds.
no code implementations • 8 Jul 2021 • Nikhil Pratap Ghanathe, Vivek Seshadri, Rahul Sharma, Steve Wilton, Aayan Kumar
Recent breakthroughs in ML have produced new classes of models that allow ML inference to run directly on milliwatt-powered IoT devices.
1 code implementation • 10 May 2021 • Deevashwer Rathee, Mayank Rathee, Rahul Kranti Kiran Goli, Divya Gupta, Rahul Sharma, Nishanth Chandran, Aseem Rastogi
Although prior work on secure 2-party inference provides specialized protocols for convolutional neural networks (CNNs), existing secure implementations of these math operators rely on generic 2-party computation (2PC) protocols that suffer from high communication.
no code implementations • 29 Mar 2021 • Rahul Sharma, Soumya Banerjee, Dootika Vats, Piyush Rai
We present a variational inference (VI) framework that unifies and leverages sequential Monte-Carlo (particle filtering) with \emph{approximate} rejection sampling to construct a flexible family of variational distributions.
no code implementations • 1 Jan 2021 • Rahul Sharma, Soumya Banerjee, Dootika Vats, Piyush Rai
Effective variational inference crucially depends on a flexible variational family of distributions.
1 code implementation • 9 Dec 2020 • Javier Alvarez-Valle, Pratik Bhatu, Nishanth Chandran, Divya Gupta, Aditya Nori, Aseem Rastogi, Mayank Rathee, Rahul Sharma, Shubham Ugare
Our first component is an end-to-end compiler from TensorFlow to a variety of MPC protocols.
Cryptography and Security
no code implementations • NeurIPS Workshop CAP 2020 • Sahil Bhatia, Saswat Padhi, Nagarajan Natarajan, Rahul Sharma, Prateek Jain
Automated synthesis of inductive invariants is an important problem in software verification.
1 code implementation • 13 Oct 2020 • Deevashwer Rathee, Mayank Rathee, Nishant Kumar, Nishanth Chandran, Divya Gupta, Aseem Rastogi, Rahul Sharma
We present CrypTFlow2, a cryptographic framework for secure inference over realistic Deep Neural Networks (DNNs) using secure 2-party computation.
no code implementations • 9 Mar 2020 • Rahul Sharma, Krishna Somandepalli, Shrikanth Narayanan
Avoiding the need for manual annotations for active speakers in visual frames, acquiring of which is very expensive, we present a weakly supervised system for the task of localizing active speakers in movie content.
no code implementations • 26 Nov 2019 • Sahil Bhatia, Saswat Padhi, Nagarajan Natarajan, Rahul Sharma, Prateek Jain
Automated synthesis of inductive invariants is an important problem in software verification.
no code implementations • 17 Sep 2019 • Rahul Sharma, Abhishek Kumar, Piyush Rai
Our inference method is based on a crucial observation that $D_\infty(p||q)$ equals $\log M(\theta)$ where $M(\theta)$ is the optimal value of the RS constant for a given proposal $q_\theta(x)$.
4 code implementations • 16 Sep 2019 • Nishant Kumar, Mayank Rathee, Nishanth Chandran, Divya Gupta, Aseem Rastogi, Rahul Sharma
Finally, to provide malicious secure MPC protocols, our third component, Aramis, is a novel technique that uses hardware with integrity guarantees to convert any semi-honest MPC protocol into an MPC protocol that provides malicious security.
no code implementations • 17 May 2019 • Saswat Padhi, Todd Millstein, Aditya Nori, Rahul Sharma
A standard approach to mitigate overfitting in machine learning is to run multiple learners with varying expressiveness in parallel.
1 code implementation • 21 Nov 2017 • Chantat Eksombatchai, Pranav Jindal, Jerry Zitao Liu, Yuchen Liu, Rahul Sharma, Charles Sugnet, Mark Ulrich, Jure Leskovec
Furthermore, we develop a graph pruning strategy at that leads to an additional 58% improvement in recommendations.
no code implementations • 7 Jul 2017 • Saswat Padhi, Rahul Sharma, Todd Millstein
We describe the LoopInvGen tool for generating loop invariants that can provably guarantee correctness of a program with respect to a given specification.
1 code implementation • 5 Aug 2016 • Osbert Bastani, Rahul Sharma, Alex Aiken, Percy Liang
We present an algorithm for synthesizing a context-free grammar encoding the language of valid program inputs from a set of input examples and blackbox access to the program.
Programming Languages