Ilya Razenshteyn

ot_estimators. Implementations of several fast approximate algorithms for geometric optimal transport (OT)

automation. Python

ciphercore. User-friendly secure computation engine based on secure multi-party computation

barlow. Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction

3db. A framework for analyzing computer vision models with simulated data

algory. Algorithms and data structures in Python

opacus. Training PyTorch models with differential privacy

emp-tool. C++

emp-ot. Oblivious Transfer, Oblivious Transfer Extension and Variations

algorithms-in-SEAL. Some algorithms for computation on encrypted data based on Microsoft SEAL

PathOHeap. Path Oblivious Heap C++ Reference Implementation

Spartan. Spartan: High-speed zkSNARKs without trusted setup

NTK4A. Code for the paper: "Tensor Programs II: Neural Tangent Kernel for Any Architecture"

DGLE. Powerful independent cross-platform engine for 2D/3D games and visualizations. Young, strong and crazy!

discrete-gaussian-differential-privacy. Code for Canonne-Kamath-Steinke paper https://arxiv.org/abs/2004.00010

robust-local-lipschitz. A Closer Look at Accuracy vs. Robustness

securenn-public. Implementation of protocols in SecureNN.

MP-SPDZ. Versatile framework for multi-party computation

TRADES. TRADES (TRadeoff-inspired Adversarial DEfense via Surrogate-loss minimization)

neural-locality-sensitive-hashing. End-to-End learning space partition for Locality Sensitive Hashing

CrypTen. A framework for Privacy Preserving Machine Learning

coronavirus. Folding@home COVID-19 efforts

COVID-19. Novel Coronavirus (COVID-19) Cases, provided by JHU CSSE

full-stack-hello. minimal instruction set and assembler/compiler for "Hello World" execution

denoised-smoothing. Provably defending pretrained classifiers including the Azure, Google, AWS, and Clarifai APIs

rs4a. Randomized Smoothing of All Shapes and Sizes (ICML 2020).

rehashing. fast kernel evaluation in high dimensions via hashing

statopt. Statistical adaptive stochastic optimization methods

semisup-adv. Semisupervised learning for adversarial robustness https://arxiv.org/pdf/1905.13736.pdf

org-sort-tasks. Functions to keep TODO tasks in orgmode sorted and organized.

OPOT. data files for comparing optimal transport algorithms

julia. The Julia Programming Language

hiring-model. Python

xbyak. A JIT assembler for x86/x64 architectures supporting FPU, MMX, SSE (1-4), AVX (1-2, 512), APX, and AVX10.2

typescript. Algebraic graphs implementation in TypeScript

binaryen. Optimizer and compiler/toolchain library for WebAssembly

assemblyscript. A TypeScript-like language for WebAssembly.

fast_adversarial. [ICLR 2020] A repository for extremely fast adversarial training using FGSM

tcs. Book in preparation: introduction to theoretical computer science

robustness. A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.

ITensor. A C++ library for efficient tensor network calculations

plundervolt. C++

systemds. An open source ML system for the end-to-end data science lifecycle

SketchyCGAL. MATLAB implementation of the Scalable Semidefinite Programming

fancy-garbling. Rust implementation of the BMR16 arithmetic garbling scheme.

sortnetopt. Lower Size Bounds for Sorting Networks

YouTokenToMe. Unsupervised text tokenizer focused on computational efficiency

learn-to-hash. Neural LSH [ICLR 2020] - Using supervised learning to produce better space partitions for fast nearest neighbor search.

unilm. Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

ap_perf_py. A Python interface to the AdversarialPrediction.jl (https://github.com/rizalzaf/AdversarialPrediction.jl).

demikernel. Kernel-Bypass LibOS Architecture

ylg. [CVPR 2020] Official Implementation: "Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models".

splot. Visualizing the activity of many concurrent processes

timeplot. Analyst's swiss army knife for visualizing data from ad-hoc log files

progtexts. TeX

DeepFovea. Neural Reconstruction for Foveated Rendering and Video Compression using Learned Statistics of Natural Videos

TreeWasserstein. Matlab code for tree-Wasserstein distance in the paper "Tree-Sliced Variants of Wasserstein Distances", NeurIPS, 2019. (Tam Le, Makoto Yamada, Kenji Fukumizu, Marco Cuturi) --- A valid positive definite Wasserstein kernel for persistence diagrams: exp(-TW/t)

grin-linkability. Grin transaction data corresponding to research on transaction linkability

mpyc. MPyC: Multiparty Computation in Python

sketch. C++ Implementations of sketch data structures with SIMD Parallelism, including Python bindings

FarManager. File and Archive Manager

GP4A. Code for NeurIPS 2019 paper: "Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes"

MPCircuits. Optimized Circuit Generation for Secure Multiparty Computation

AgnosticMeanAndCovarianceCode. Agnostic Mean estimation code for the paper "Agnostic Estimation of Mean and Covariance"

toy_tsp. Toy TSP solver

hl. Hub Labeling Algorithms Implementation

scGeneFit-python. Python code for genetic marker selection using linear programming

xena. Lean Library currently studying for a degree at Imperial College

NeurIPS-2019-Stats. General stats about NeurIPS 2019

POT. POT : Python Optimal Transport

dune. A composable build system for OCaml.

ungoogled-chromium. Google Chromium, sans integration with Google

spiral. We provide a pre-trained model for unconditional 19-step generation of CelebA-HQ images

fair_clustering. Python

znn-release. Multi-core CPU implementation of deep learning for 2D and 3D sliding window convolutional networks (ConvNets).

columnar. High-throughput columnar serialization in Rust

support. Support size estimator

contextlocnet. ContextLocNet: Context-aware Deep Network Models for Weakly Supervised Localization (ECCV 2016)

engine. A reference implementation of the Russian GOST crypto algorithms for OpenSSL

cil. C Intermediate Language

pytorch-classification. Classification with PyTorch.

taco. The Tensor Algebra Compiler (taco) computes sparse tensor expressions on CPUs and GPUs

8cc. A Small C Compiler

nqcc. A compiler for a tiny (but growing!) subset of C, written in OCaml.

puffinn. Parameterless and Universal FInding of Nearest Neighbors

private-join-and-compute. C++

robustness_applications. Notebooks for reproducing the paper "Computer Vision with a Single (Robust) Classifier"

polyhedra-correction-library. Code of my qualification and PhD works: reconstruction and correction of 3D polyhedra from shadow contours

adversarial-nonparametrics. Robustness for Non-Parametric Classification: A Generic Attack and Defense

robust-filter. [ICML 2017] Robust estimation of mean and covariance in high dimensions

CIFAR-10.1. Release of CIFAR-10.1, a new test set for CIFAR-10.

ImageNetV2. A new test set for ImageNet

Flash. LSH-GPU ANN package

Estimate_CC. C++

HashingDeepLearning. Codebase for "SLIDE : In Defense of Smart Algorithms over Hardware Acceleration for Large-Scale Deep Learning Systems"

smoothing-adversarial. Code replicating the results of our "Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers" paper.

smoothing-adversarial. Code for our NeurIPS 2019 *spotlight* "Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers"

EzPC. C++

YOPO-You-Only-Propagate-Once. Code for our nips19 paper: You Only Propagate Once: Accelerating Adversarial Training Via Maximal Principle

dfs-kotlin-benchmark. Lets try to figure out, why dfs written in kotlin is so slow

knn_vgg. Epic comparison between feature clustering vs additional layers with various numbers of layers peeled off from VGG.

pygcn. Graph Convolutional Networks in PyTorch

tpu. Reference models and tools for Cloud TPUs.

learning-to-route. Code for ICML2019 paper: Learning to Route in Similarity Graphs

ru.javascript.info. Современный учебник JavaScript

react-katex. Display math in TeX with KaTeX and ReactJS

algoprog. CoffeeScript

SPTAG. A distributed approximate nearest neighborhood search (ANN) library which provides a high quality vector index build, search and distributed online serving toolkits for large scale vector search scenario.

spcppl. Prewritten code library for programming contests

testlib.hpp. Yet another testlib

conv-sv. The Singular Values of Convolutional Layers

C-to-Forth-compiler. Few people use Forth. But this might be useful if you want to!

spreadingvectors. Open source implementation of "Spreading Vectors for Similarity Search"

opc. One Page CPU Project - CPU, Assembler & Emulator each in a single page of code

robust-verify-benchmark. Benchmark for LP-relaxed robustness verification of ReLU-networks

BosqueLanguage. The Bosque programming language is an experiment in regularized design for a machine assisted rapid and reliable software development lifecycle.

neural-tangents. Fast and Easy Infinite Neural Networks in Python

private-ai-resources. SOON TO BE DEPRECATED - Private machine learning progress

sisc. Second Interpreter of Scheme Code [unofficial maintenance fork]

biwascheme. Scheme interpreter written in JavaScript

schemely. Scheme plugin for IntelliJ

intellij-scheme. IntelliJ plugin for Scheme programming language

DMM. Data Flow Matrix Machines. Generalization of recurrent neural networks.

simd_interleave. Interleaving bits from two sources using SIMD instructions.

graph-based-code-modelling. Code for "Generative Code Modeling with Graphs" (ICLR'19)

libOTe. A fast, portable, and easy to use Oblivious Transfer Library

deep-q-drive. Simple implementation of deep q-learning and driving environment

self-attention-gan. Python

smoothing. Provable adversarial robustness at ImageNet scale

LSH_Memory. One-Shot Learning using Nearest-Neighbor Search (NNS) and Locality-Sensitive Hashing LSH

Fair-Regression. Code and simulated data for the paper “Fair Regression for Health Care Spending”

GP-EST. Bayesian optimization with the Gaussian process assumption

pytorch_kmeans. Implementation of the k-means algorithm in PyTorch that works for large datasets

funML. Machine learning algorithms.

aggregator. TCS Aggregator

NGT. Nearest Neighbor Search with Neighborhood Graph and Tree for High-dimensional Data

algorithms. Bug-tracking for Jeff's algorithms book, notes, etc.

privacy. Library for training machine learning models with privacy for training data

rapid. Rapid is a scalable distributed membership service

PQCrypto-LWEKE. FrodoKEM: Learning with Errors Key Encapsulation. FrodoKEM is a family of key-encapsulation mechanisms that are designed to be conservative yet practical post-quantum constructions whose security derives from cautious parameterizations of the well-studied learning with errors problem.

obliv-c. C

sql-differential-privacy. Dataflow analysis & differential privacy for SQL queries. This project is deprecated and not maintained.

SEAL. Microsoft SEAL is an easy-to-use and powerful homomorphic encryption library.

MISSION. MISSION: Ultra Large-Scale Feature Selection using Count-Sketches

schm. C++

slalom. Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware

IPO-Review-Chapter. Explanation of IPO data extraction from SDC Platinum, data cleaning and matching with CRSP

Where-s-That-Paper-. A Chrome extension that automatically adds viewed academic papers to your favorites.

man-intrinsics. Create man pages from information used by Intel Intrinsics Guide and optionally uops.info

fsck. Check and fix UNIX xv6 file system damages.

phabricator. Effective June 1, 2021: Phabricator is no longer actively maintained.

tf-encrypted. A Framework for Encrypted Machine Learning in TensorFlow

hazel. Hazel, a live functional programming environment with typed holes

openenclave. SDK for developing enclaves

gazelle_mpc. C++

jsnark. A Java library for zk-SNARK circuits

tfhe. TFHE: Fast Fully Homomorphic Encryption Library over the Torus

MST. Java

py-spy. Sampling profiler for Python programs

hadamard_response. Hadamard Response: Communication efficient, sample optimal, linear time locally private learning of distributions

jheaps. Master repository for the JHeaps project

TinyGarble. TinyGarble: Logic Synthesis and Sequential Descriptions for Yao's Garbled Circuits

Brain-Computer-Interface-BCI-based-on-Steady-State-Visual-Evoked-Potential-SSVEP-. MATLAB

bcg. Blended Conditional Gradient (BCG) Algorithm Package in Python

dbn_upper_bound. Computational effort to upper bound the de Bruijn-Newman constant as part of a Polymath project

adversarial-logit-pairing-analysis. Analysis of Adversarial Logit Pairing

grumpy. Minimalistic blog engine

ENCRYPTO_utils. Crypto and networking utils used for ABY and OTExtension

MIRACL. MIRACL Cryptographic SDK: Multiprecision Integer and Rational Arithmetic Cryptographic Library is a C software library that is widely regarded by developers as the gold standard open source SDK for elliptic curve cryptography (ECC).

awesome-mpc. A curated list of multi party computation resources and links.

zkledger. Privacy-preserving auditing for distributed ledgers

OTExtension. C++ OT extension implementation

ABY. ABY - A Framework for Efficient Mixed-protocol Secure Two-party Computation

icfpc2017-kontur-ru. kontur.ru team @ ICFPC 2017

robust-features-code. Code for "Robustness May Be at Odds with Accuracy"

RHash. Great utility for computing hash sums

yugabyte-db. YugabyteDB - the cloud native distributed SQL database for mission-critical applications.

lightspeed. lightspeed matlab toolbox

tarsnap. Command-line client code for Tarsnap.

blasjs. Pure Javascript manually written :ok_hand: implementation of BLAS, Many numerical software applications use BLAS computations, including Armadillo, LAPACK, LINPACK, GNU Octave, Mathematica, MATLAB, NumPy, R, and Julia.

GNOIMI. C++

HJW_KL_divergence_estimator. Python

KaHIP. KaHIP -- HIGH Quality Partitioning.

Translator-HumanParityData. Human evaluation results and translation output for the Translator Human Parity Data release

entropy. Entropy estimator

Lol. Λ ⚬ λ: Functional Lattice Cryptography

hillview. Big data spreadsheet

Harmonica. Code repository for the paper "Hyperparameter Optimization: A Spectral Approach" by Elad Hazan, Adam Klivans, Yang Yuan.

fastchess. Predicts the best chess move with 27.5% accuracy by a single matrix multiplication

bksvd. Fast randomized block Krylov method for the singular value decomposition

GHMatch. GHMatch code for https://arxiv.org/pdf/1610.05214.pdf

QAP_pt. C

eigen-git-mirror. THIS MIRROR IS DEPRECATED -- New url: https://gitlab.com/libeigen/eigen

EdgeML. This repository provides code for machine learning algorithms for edge devices developed at Microsoft Research India.

manim. Animation engine for explanatory math videos

StreamingCC. A C++ library for summarizing data streams

optimistic_GAN_training. Jupyter Notebook

quadsketch. Implementation of QuadSketch algorithm

LuSTScenario. Luxembourg SUMO Traffic (LuST) Scenario

Laplacians.jl. Algorithms inspired by graph Laplacians: linear equation solvers, sparsification, clustering, optimization, etc.