Search Results for author: Arash Mehrjou

Found 35 papers, 12 papers with code

DiscoBAX: Discovery of Optimal Intervention Sets in Genomic Experiment Design

1 code implementation7 Dec 2023 Clare Lyle, Arash Mehrjou, Pascal Notin, Andrew Jesson, Stefan Bauer, Yarin Gal, Patrick Schwab

The discovery of therapeutics to treat genetically-driven pathologies relies on identifying genes involved in the underlying disease mechanisms.

Experimental Design

Multi-omics Prediction from High-content Cellular Imaging with Deep Learning

1 code implementation15 Jun 2023 Rahil Mehrizi, Arash Mehrjou, Maryana Alegro, Yi Zhao, Benedetta Carbone, Carl Fishwick, Johanna Vappiani, Jing Bi, Siobhan Sanford, Hakan Keles, Marcus Bantscheff, Cuong Nguyen, Patrick Schwab

High-content cellular imaging, transcriptomics, and proteomics data provide rich and complementary views on the molecular layers of biology that influence cellular states and function.

Federated Causal Discovery From Interventions

3 code implementations7 Nov 2022 Amin Abyaneh, Nino Scherrer, Patrick Schwab, Stefan Bauer, Bernhard Schölkopf, Arash Mehrjou

We propose FedCDI, a federated framework for inferring causal structures from distributed data containing interventional samples.

Causal Discovery Federated Learning +1

From Points to Functions: Infinite-dimensional Representations in Diffusion Models

1 code implementation25 Oct 2022 Sarthak Mittal, Guillaume Lajoie, Stefan Bauer, Arash Mehrjou

Consequently, it is reasonable to ask if there is an intermediate time step at which the preserved information is optimal for a given downstream task.

GalilAI: Out-of-Task Distribution Detection using Causal Active Experimentation for Safe Transfer RL

no code implementations29 Oct 2021 Sumedh A Sontakke, Stephen Iota, Zizhao Hu, Arash Mehrjou, Laurent Itti, Bernhard Schölkopf

Extending the successes in supervised learning methods to the reinforcement learning (RL) setting, however, is difficult due to the data generating process - RL agents actively query their environment for data, and the data are a function of the policy followed by the agent.

Out of Distribution (OOD) Detection Reinforcement Learning (RL)

GeneDisco: A Benchmark for Experimental Design in Drug Discovery

2 code implementations ICLR 2022 Arash Mehrjou, Ashkan Soleymani, Andrew Jesson, Pascal Notin, Yarin Gal, Stefan Bauer, Patrick Schwab

GeneDisco contains a curated set of multiple publicly available experimental data sets as well as open-source implementations of state-of-the-art active learning policies for experimental design and exploration.

Active Learning Drug Discovery +1

Federated Learning as a Mean-Field Game

no code implementations8 Jul 2021 Arash Mehrjou

We establish a connection between federated learning, a concept from machine learning, and mean-field games, a concept from game theory and control theory.

Federated Learning Privacy Preserving

Representation Learning in Continuous-Time Score-Based Generative Models

no code implementations ICML Workshop INNF 2021 Korbinian Abstreiter, Stefan Bauer, Arash Mehrjou

Score-based methods represented as stochastic differential equations on a continuous time domain have recently proven successful as a non-adversarial generative model.

Denoising Representation Learning

Diffusion-Based Representation Learning

no code implementations29 May 2021 Korbinian Abstreiter, Sarthak Mittal, Stefan Bauer, Bernhard Schölkopf, Arash Mehrjou

In contrast, the introduced diffusion-based representation learning relies on a new formulation of the denoising score matching objective and thus encodes the information needed for denoising.

Denoising Representation Learning +1

Pyfectious: An individual-level simulator to discover optimal containment polices for epidemic diseases

1 code implementation24 Mar 2021 Arash Mehrjou, Ashkan Soleymani, Amin Abyaneh, Samir Bhatt, Bernhard Schölkopf, Stefan Bauer

Simulating the spread of infectious diseases in human communities is critical for predicting the trajectory of an epidemic and verifying various policies to control the devastating impacts of the outbreak.

Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning

1 code implementation7 Oct 2020 Sumedh A. Sontakke, Arash Mehrjou, Laurent Itti, Bernhard Schölkopf

Inspired by this, we attempt to equip reinforcement learning agents with the ability to perform experiments that facilitate a categorization of the rolled-out trajectories, and to subsequently infer the causal factors of the environment in a hierarchical manner.

Representation Learning Zero-Shot Learning

Real-time Prediction of COVID-19 related Mortality using Electronic Health Records

no code implementations31 Aug 2020 Patrick Schwab, Arash Mehrjou, Sonali Parbhoo, Leo Anthony Celi, Jürgen Hetzel, Markus Hofer, Bernhard Schölkopf, Stefan Bauer

Coronavirus Disease 2019 (COVID-19) is an emerging respiratory disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) with rapid human-to-human transmission and a high case fatality rate particularly in older patients.

Specificity

Learning Dynamical Systems using Local Stability Priors

no code implementations23 Aug 2020 Arash Mehrjou, Andrea Iannelli, Bernhard Schölkopf

A coupled computational approach to simultaneously learn a vector field and the region of attraction of an equilibrium point from generated trajectories of the system is proposed.

Neural Lyapunov Redesign

1 code implementation6 Jun 2020 Arash Mehrjou, Mohammad Ghavamzadeh, Bernhard Schölkopf

We provide theoretical results on the class of systems that can be treated with the proposed algorithm and empirically evaluate the effectiveness of our method using an exemplary dynamical system.

Kernel-Guided Training of Implicit Generative Models with Stability Guarantees

no code implementations29 Oct 2019 Arash Mehrjou, Wittawat Jitkrittum, Krikamol Muandet, Bernhard Schölkopf

Modern implicit generative models such as generative adversarial networks (GANs) are generally known to suffer from issues such as instability, uninterpretability, and difficulty in assessing their performance.

Dual Instrumental Variable Regression

1 code implementation NeurIPS 2020 Krikamol Muandet, Arash Mehrjou, Si Kai Lee, Anant Raj

We present a novel algorithm for non-linear instrumental variable (IV) regression, DualIV, which simplifies traditional two-stage methods via a dual formulation.

regression

The Incomplete Rosetta Stone Problem: Identifiability Results for Multi-View Nonlinear ICA

no code implementations16 May 2019 Luigi Gresele, Paul K. Rubenstein, Arash Mehrjou, Francesco Locatello, Bernhard Schölkopf

In contrast to known identifiability results for nonlinear ICA, we prove that independent latent sources with arbitrary mixing can be recovered as long as multiple, sufficiently different noisy views are available.

Learning from Samples of Variable Quality

no code implementations ICLR Workshop LLD 2019 Mostafa Dehghani, Arash Mehrjou, Stephan Gouws, Jaap Kamps, Bernhard Schölkopf

Training labels are expensive to obtain and may be of varying quality, as some may be from trusted expert labelers while others might be from heuristics or other sources of weak supervision such as crowd-sourcing.

Kernel-Guided Training of Implicit Generative Models with Stability Guarantees

no code implementations26 Jan 2019 Arash Mehrjou, Wittawat Jitkrittum, Krikamol Muandet, Bernhard Schölkopf

Modern implicit generative models such as generative adversarial networks (GANs) are generally known to suffer from issues such as instability, uninterpretability, and difficulty in assessing their performance.

Counterfactuals uncover the modular structure of deep generative models

no code implementations ICLR 2020 Michel Besserve, Arash Mehrjou, Rémy Sun, Bernhard Schölkopf

Deep generative models can emulate the perceptual properties of complex image datasets, providing a latent representation of the data.

counterfactual Style Transfer

Deep Nonlinear Non-Gaussian Filtering for Dynamical Systems

no code implementations14 Nov 2018 Arash Mehrjou, Bernhard Schölkopf

Filtering is a general name for inferring the states of a dynamical system given observations.

A Local Information Criterion for Dynamical Systems

no code implementations27 May 2018 Arash Mehrjou, Friedrich Solowjow, Sebastian Trimpe, Bernhard Schölkopf

Apart from its application for encoding a sequence of observations, we propose to use the compression achieved by this encoding as a criterion for model selection.

Model Selection

Distribution Aware Active Learning

no code implementations23 May 2018 Arash Mehrjou, Mehran Khodabandeh, Greg Mori

This strategy does not make good use of the structure of the dataset at hand and is prone to be misguided by outliers.

Active Learning

Deep Energy Estimator Networks

1 code implementation21 May 2018 Saeed Saremi, Arash Mehrjou, Bernhard Schölkopf, Aapo Hyvärinen

We present the utility of DEEN in learning the energy, the score function, and in single-step denoising experiments for synthetic and high-dimensional data.

Denoising Density Estimation

Analysis of Nonautonomous Adversarial Systems

no code implementations13 Mar 2018 Arash Mehrjou

In this note, we show by a simple example how annealing strategy works in GANs.

Tempered Adversarial Networks

no code implementations ICML 2018 Mehdi S. M. Sajjadi, Giambattista Parascandolo, Arash Mehrjou, Bernhard Schölkopf

A possible explanation for training instabilities is the inherent imbalance between the networks: While the discriminator is trained directly on both real and fake samples, the generator only has control over the fake samples it produces since the real data distribution is fixed by the choice of a given dataset.

Fidelity-Weighted Learning

no code implementations ICLR 2018 Mostafa Dehghani, Arash Mehrjou, Stephan Gouws, Jaap Kamps, Bernhard Schölkopf

To this end, we propose "fidelity-weighted learning" (FWL), a semi-supervised student-teacher approach for training deep neural networks using weakly-labeled data.

Ad-Hoc Information Retrieval Information Retrieval +1

Annealed Generative Adversarial Networks

no code implementations21 May 2017 Arash Mehrjou, Bernhard Schölkopf, Saeed Saremi

We introduce a novel framework for adversarial training where the target distribution is annealed between the uniform distribution and the data distribution.

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