1 code implementation • 16 Apr 2024 • J. Pablo Muñoz, Jinjie Yuan, Nilesh Jain
Recently, several approaches successfully demonstrated that weight-sharing Neural Architecture Search (NAS) can effectively explore a search space of elastic low-rank adapters (LoRA), allowing the parameter-efficient fine-tuning (PEFT) and compression of large language models.
no code implementations • 12 May 2023 • Gopi Krishna Jha, Anthony Thomas, Nilesh Jain, Sameh Gobriel, Tajana Rosing, Ravi Iyer
Deep learning-based recommendation systems (e. g., DLRMs) are widely used AI models to provide high-quality personalized recommendations.
no code implementations • 20 Sep 2022 • Anthony Thomas, Behnam Khaleghi, Gopi Krishna Jha, Sanjoy Dasgupta, Nageen Himayat, Ravi Iyer, Nilesh Jain, Tajana Rosing
Hyperdimensional computing (HDC) is a paradigm for data representation and learning originating in computational neuroscience.
no code implementations • 15 Sep 2022 • Yash Akhauri, J. Pablo Munoz, Nilesh Jain, Ravi Iyer
Our methodology efficiently discovers an interpretable and generalizable zero-cost proxy that gives state of the art score-accuracy correlation on all datasets and search spaces of NASBench-201 and Network Design Spaces (NDS).
no code implementations • NeurIPS Workshop AIPLANS 2021 • Yash Akhauri, Juan Pablo Munoz, Ravishankar Iyer, Nilesh Jain
Neural networks are becoming increasingly ubiquitous in a wide range of use cases.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
no code implementations • 17 Jun 2021 • Yash Akhauri, Adithya Niranjan, J. Pablo Muñoz, Suvadeep Banerjee, Abhijit Davare, Pasquale Cocchini, Anton A. Sorokin, Ravi Iyer, Nilesh Jain
The rapidly evolving field of Artificial Intelligence necessitates automated approaches to co-design neural network architecture and neural accelerators to maximize system efficiency and address productivity challenges.
no code implementations • 14 Jun 2021 • Santiago Miret, Vui Seng Chua, Mattias Marder, Mariano Phielipp, Nilesh Jain, Somdeb Majumdar
In this work, we present a flexible and scalable framework for automated mixed-precision quantization that concurrently optimizes task performance, memory compression, and compute savings through multi-objective evolutionary computing.