Yashas Annadani

PhD Student, Technical University of Munich and Helmholtz AI

FIRSTNAME [DOT] LASTNAME [AT] gmail.com

Bio

I am a PhD student in Causal Inference and Machine Learning at Technical University of Munich and Helmholtz AI advised by Stefan Bauer. I am also part of the ELLIS doctoral program at Max Planck Institute for Intelligent Systems co-supervised by Bernhard Schölkopf. During the course of my PhD, I have also spent time at KTH Stockholm, Sweden and Microsoft Research Cambridge, UK. Before this, I completed my master's degree in Electrical Engineeting and Information Technology at ETH Zürich in 2021. During my master's studies, I was a research intern at Mila under the supervision of Yoshua Bengio.

Publications/Preprints

BayesDAG: Gradient-Based Posterior Sampling for Causal Discovery

Yashas Annadani*, Nick Pawlowski, Joel Jennings, Stefan Bauer, Cheng Zhang, Wenbo Gong*

In advances of Neural Information Processing Systems (NeurIPS), 2023

Trust Your Gradients: Gradient-based Intervention Targeting for Causal Discovery

Mateusz Olko*, Michal Zajac*, Aleksandra Nowak*, Nino Scherrer, Yashas Annadani, Stefan Bauer, Lukasz Kucinski, Piotr Milos

In advances of Neural Information Processing Systems (NeurIPS), 2023

Differentiable Multi-Target Causal Bayesian Experimental Design

Yashas Annadani*, Panagiotis Tigas*, Desi R. Ivanova, Andrew Jesson, Yarin Gal, Adam Foster^, Stefan Bauer^

In International Conference on Machine Learning (ICML), 2023

Structure by Architecture: Structured Representations without Regularization.

Felix Leeb, Giulia Lanzillotta, Yashas Annadani, Michel Besserve, Stefan Bauer, Bernhard Schölkopf

In International Conference on Learning Representations (ICLR), 2023

Interventions, Where and How? Experimental Design for Causal Models at Scale

Panagiotis Tigas*, Yashas Annadani*, Andrew Jesson, Bernhard Schölkopf, Yarin Gal, Stefan Bauer

In advances of Neural Information Processing Systems (NeurIPS), 2022

Learning Neural Causal Models with Active Interventions

Nino Scherrer, Olexa Bilaniuk, Yashas Annadani, Anirudh Goyal, Patrick Schwab, Bernhard Schölkopf, Michael Curtis Mozer, Yoshua Bengio, Stefan Bauer, Nan Rosemary Ke

arxiv preprint: arXiv:2109.02429. In NeurIPS workshop Causal Inference & Machine Learning: Why now? (WHY-21), 2021

Variational Causal Networks: Approximate Bayesian Inference over Causal Structures

Yashas Annadani, Jonas Rothfuss, Alexandre Lacoste, Nino Scherrer, Anirudh Goyal, Yoshua Bengio, Stefan Bauer

arxiv preprint: arXiv:2106.07635. Oral at KDD Workshop on Bayesian causal inference for real world interactive systems, 2021

Preserving Semantic Relations for Zero-Shot Learning

Yashas Annadani, Soma Biswas

In IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2018

Growbit: Incremental Hashing for Cross-Modal Retrieval

Devraj Mandal, Yashas Annadani, Soma Biswas

In Asian Conference on Computer Vision (ACCV), 2018

Augment and Adapt: A Simple Approach to Image Tampering Detection

Yashas Annadani, C.V. Jawahar

In IEEE International Conference on Pattern Recognition (ICPR), 2018