activity
20102021
most citedProtection Against Reconstruction and Its Applications in Private Federated Learning

257 citations · 271 across the 8 of their papers we have counts for

collaborators

12 papers

cs.LG2021★ 2 cited

Federated Evaluation and Tuning for On-Device Personalization: System Design & Applications

Matthias Paulik, Matt Seigel, Henry Mason +19

We describe the design of our federated task processing system. Originally, the system was created to support two specific federated tasks: evaluation and tuning of on-device ML sy…

stat.ML2018★ 257 cited

Protection Against Reconstruction and Its Applications in Private Federated Learning

Abhishek Bhowmick, John Duchi, Julien Freudiger +2

In large-scale statistical learning, data collection and model fitting are moving increasingly toward peripheral devices---phones, watches, fitness trackers---away from centralized…

cs.CE2015★ 1 cited

Quantifying and Visualizing Uncertainties in Molecular Models

Muhibur Rasheed, Nathan Clement, Abhishek Bhowmick +1

Computational molecular modeling and visualization has seen significant progress in recent years with sev- eral molecular modeling and visualization software systems in use today.…

cs.DM2015

Bias vs structure of polynomials in large fields, and applications in information theory

Abhishek Bhowmick, Shachar Lovett

Let be a polynomial of degree in variables over a finite field . The polynomial is said to be unbiased if the distribution of for a uniform input $x…

cs.DS2015

Using higher-order Fourier analysis over general fields

Arnab Bhattacharyya, Abhishek Bhowmick

Higher-order Fourier analysis, developed over prime fields, has been recently used in different areas of computer science, including list decoding, algorithmic decomposition and te…

math.NT2014

On primitive elements in finite fields of low characteristic

Abhishek Bhowmick, Thái Hoàng Lê

We discuss the problem of constructing a small subset of a finite field containing primitive elements of the field. Given a finite field, , small and large $n…

cs.CC2014

Nonclassical polynomials as a barrier to polynomial lower bounds

Abhishek Bhowmick, Shachar Lovett

The problem of constructing explicit functions which cannot be approximated by low degree polynomials has been extensively studied in computational complexity, motivated by applica…

cs.CG2014★ 5 cited

On Low Discrepancy Samplings in Product Spaces of Motion Groups

Chandrajit Bajaj, Abhishek Bhowmick, Eshan Chattopadhyay +1

Deterministically generating near-uniform point samplings of the motion groups like SO(3), SE(3) and their n-wise products SO(3)^n, SE(3)^n is fundamental to numerous applications…

cs.CC2014

Deterministic Extractors for Additive Sources

Abhishek Bhowmick, Ariel Gabizon, Thái Hoàng Lê +1

We propose a new model of a weakly random source that admits randomness extraction. Our model of additive sources includes such natural sources as uniform distributions on arithmet…

cs.CC2014★ 3 cited

List decoding Reed-Muller codes over small fields

Abhishek Bhowmick, Shachar Lovett

The list decoding problem for a code asks for the maximal radius up to which any ball of that radius contains only a constant number of codewords. The list decoding radius is not w…

cs.CC2012★ 2 cited

New Lower Bounds for Matching Vector Codes

Abhishek Bhowmick, Zeev Dvir, Shachar Lovett

A Matching Vector (MV) family modulo is a pair of ordered lists and where with the following inner product patt…

cs.DB2010★ 1 cited

Finding top-k similar pairs of objects annotated with terms from an ontology

Arnab Bhattacharya, Abhishek Bhowmick, Ambuj K. Singh

With the growing focus on semantic searches and interpretations, an increasing number of standardized vocabularies and ontologies are being designed and used to describe data. We i…