Search Results for author: Igor Fedorov

Found 22 papers, 7 papers with code

Rankitect: Ranking Architecture Search Battling World-class Engineers at Meta Scale

no code implementations14 Nov 2023 Wei Wen, Kuang-Hung Liu, Igor Fedorov, Xin Zhang, Hang Yin, Weiwei Chu, Kaveh Hassani, Mengying Sun, Jiang Liu, Xu Wang, Lin Jiang, Yuxin Chen, Buyun Zhang, Xi Liu, Dehua Cheng, Zhengxing Chen, Guang Zhao, Fangqiu Han, Jiyan Yang, Yuchen Hao, Liang Xiong, Wen-Yen Chen

In industry system, such as ranking system in Meta, it is unclear whether NAS algorithms from the literature can outperform production baselines because of: (1) scale - Meta ranking systems serve billions of users, (2) strong baselines - the baselines are production models optimized by hundreds to thousands of world-class engineers for years since the rise of deep learning, (3) dynamic baselines - engineers may have established new and stronger baselines during NAS search, and (4) efficiency - the search pipeline must yield results quickly in alignment with the productionization life cycle.

Neural Architecture Search

DistDNAS: Search Efficient Feature Interactions within 2 Hours

no code implementations1 Nov 2023 Tunhou Zhang, Wei Wen, Igor Fedorov, Xi Liu, Buyun Zhang, Fangqiu Han, Wen-Yen Chen, Yiping Han, Feng Yan, Hai Li, Yiran Chen

To optimize search efficiency, DistDNAS distributes the search and aggregates the choice of optimal interaction modules on varying data dates, achieving over 25x speed-up and reducing search cost from 2 days to 2 hours.

Recommendation Systems

PerfSAGE: Generalized Inference Performance Predictor for Arbitrary Deep Learning Models on Edge Devices

no code implementations26 Jan 2023 Yuji Chai, Devashree Tripathy, Chuteng Zhou, Dibakar Gope, Igor Fedorov, Ramon Matas, David Brooks, Gu-Yeon Wei, Paul Whatmough

The ability to accurately predict deep neural network (DNN) inference performance metrics, such as latency, power, and memory footprint, for an arbitrary DNN on a target hardware platform is essential to the design of DNN based models.

Restructurable Activation Networks

1 code implementation17 Aug 2022 Kartikeya Bhardwaj, James Ward, Caleb Tung, Dibakar Gope, Lingchuan Meng, Igor Fedorov, Alex Chalfin, Paul Whatmough, Danny Loh

To address this question, we propose a new paradigm called Restructurable Activation Networks (RANs) that manipulate the amount of non-linearity in models to improve their hardware-awareness and efficiency.

object-detection Object Detection

Magnitude-aware Probabilistic Speaker Embeddings

1 code implementation28 Feb 2022 Nikita Kuzmin, Igor Fedorov, Alexey Sholokhov

We propose a new probabilistic speaker embedding extractor using the information encoded in the embedding magnitude and leverage it in the speaker verification pipeline.

Out-of-Distribution Detection Speaker Verification

Hybrid Cloud-Edge Networks for Efficient Inference

1 code implementation29 Sep 2021 Anil Kag, Igor Fedorov, Aditya Gangrade, Paul Whatmough, Venkatesh Saligrama

The first network is a low-capacity network that can be deployed on an edge device, whereas the second is a high-capacity network deployed in the cloud.

TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids

1 code implementation20 May 2020 Igor Fedorov, Marko Stamenovic, Carl Jensen, Li-Chia Yang, Ari Mandell, Yiming Gan, Matthew Mattina, Paul N. Whatmough

Modern speech enhancement algorithms achieve remarkable noise suppression by means of large recurrent neural networks (RNNs).

Model Compression Quantization +1

Pushing the limits of RNN Compression

no code implementations4 Oct 2019 Urmish Thakker, Igor Fedorov, Jesse Beu, Dibakar Gope, Chu Zhou, Ganesh Dasika, Matthew Mattina

This paper introduces a method to compress RNNs for resource constrained environments using Kronecker product (KP).

Compressing RNNs for IoT devices by 15-38x using Kronecker Products

no code implementations7 Jun 2019 Urmish Thakker, Jesse Beu, Dibakar Gope, Chu Zhou, Igor Fedorov, Ganesh Dasika, Matthew Mattina

Recurrent Neural Networks (RNN) can be difficult to deploy on resource constrained devices due to their size. As a result, there is a need for compression techniques that can significantly compress RNNs without negatively impacting task accuracy.

SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers

no code implementations NeurIPS 2019 Igor Fedorov, Ryan P. Adams, Matthew Mattina, Paul N. Whatmough

The vast majority of processors in the world are actually microcontroller units (MCUs), which find widespread use performing simple control tasks in applications ranging from automobiles to medical devices and office equipment.

BIG-bench Machine Learning Neural Architecture Search

Multimodal Sparse Bayesian Dictionary Learning

no code implementations10 Apr 2018 Igor Fedorov, Bhaskar D. Rao

This paper addresses the problem of learning dictionaries for multimodal datasets, i. e. datasets collected from multiple data sources.

Dictionary Learning

Re-Weighted Learning for Sparsifying Deep Neural Networks

no code implementations5 Feb 2018 Igor Fedorov, Bhaskar D. Rao

This paper addresses the topic of sparsifying deep neural networks (DNN's).

Relevance Subject Machine: A Novel Person Re-identification Framework

no code implementations30 Mar 2017 Igor Fedorov, Ritwik Giri, Bhaskar D. Rao, Truong Q. Nguyen

We propose a novel method called the Relevance Subject Machine (RSM) to solve the person re-identification (re-id) problem.

Person Re-Identification

Robust Bayesian Method for Simultaneous Block Sparse Signal Recovery with Applications to Face Recognition

no code implementations6 May 2016 Igor Fedorov, Ritwik Giri, Bhaskar D. Rao, Truong Q. Nguyen

In this paper, we present a novel Bayesian approach to recover simultaneously block sparse signals in the presence of outliers.

Face Recognition

A Unified Framework for Sparse Non-Negative Least Squares using Multiplicative Updates and the Non-Negative Matrix Factorization Problem

no code implementations7 Apr 2016 Igor Fedorov, Alican Nalci, Ritwik Giri, Bhaskar D. Rao, Truong Q. Nguyen, Harinath Garudadri

We show that the proposed framework encompasses a large class of S-NNLS algorithms and provide a computationally efficient inference procedure based on multiplicative update rules.

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