Nino Scherrer

<firstname>.<lastname>@gmail.com

I am currently a visiting researcher at FAR AI working with Claudia Shi (Columbia) and Amir Feder (Columbia/Google). We investigate the effects of training data, optimization formulations and fine-tuning procedures on language model behaviors and demographic biases.

Previously, I spent time as a research intern at the Vector Institute (hosted by Prof. Animesh Garg) and Mila (hosted by Prof. Yoshua Bengio), and for my master thesis at MPI for Intelligent Systems, Tübingen. During this research visits, I have been fortunate to work closely with Nan Rosemary Ke, Anirudh Goyal and Prof. Stefan Bauer.

I did my masters and bachelors in computer science at ETH Zürich. In my earlier life, I did a diploma (vocational education) in computer science and worked multiple years as a systems engineer at SFS AG.

Fields of Interest

Causal Inference Representation Learning Natural Language Processing AI for Healthcare

Research

Trust Your ∇: Gradient-based Intervention Targeting for Causal Discovery
Mateusz Olko*, Michał Zając*, Aleksandra Nowak*, Nino Scherrer, Yashas Annadani, Stefan Bauer, Łukasz Kuciński, Piotr Miłoś
Preprint (arXiv) & NeurIPS 2022 Workshop on Causality for Real-world Impact ,
[Paper]

Causal Discovery

Experimental Design
On the Generalization and Adaption Performance of Causal Models
Nino Scherrer, Anirudh Goyal, Stefan Bauer, Yoshua Bengio, & Nan Rosemary Ke,
Preprint (arXiv) & ICML 2022 - SCIS and BeyondBayes Workshop,
[Paper]

Causal Models

Zero- and Few-Shot Adaptation
Learning Neural Causal Models with Active Interventions
Nino Scherrer, Olexa Bilaniuk, Yashas Annadani, Anirudh Goyal, Patrick Schwab, Bernhard Schölkopf, Michael C. Mozer, Yoshua Bengio, Stefan Bauer & Nan Rosemary Ke,
Preprint (arXiv) & NeurIPS WHY-21 Workshop, 2021,
[Paper] [Blog]

Causal Discovery

Experimental Design
Variational Causal Networks: Approximate Bayesian Inference over Causal Structures
Yashas Annadani, Jonas Rothfuss, Alexandre Lacoste, Nino Scherrer, Anirudh Goyal, Yoshua Bengio & Stefan Bauer,
Preprint (arXiv) & KDD - BCIRWIS Workshop, 2021,
[Paper] [Code]

Causal Discovery

Variational Inference
Improved Segmentation and Detection Sensitivity of Diffusion-weighted Stroke Lesions with Synthetically Enhanced Deep Learning
Christian Federau, Soren Christensen, Nino Scherrer, Johanna M. Ospel, Victor Schulze-Zachau, Noemi Schmidt, Hannes-Christian Breit, Julian Macclaren, Maarten Lansberg & Sebastian Kozerke,
Radiology: Artificial Intelligence, 2020,
[Paper]

Medical Image Analysis

Semantic Segmentation

Tutorial

I helped to create the ICML 2022 Tutorial on "Causality and Deep Learning: Synergies, Challenges and the Future". The corresponding work (systematic survey) "Deep Learning for Causality: A Unifying Perspective on Neural Causal Structure Learning" will be released soon.

Talks

February 2023: "Deep Learning for Causality: Neural Causal Structure Learning", AI for Actionable Impact (AI4AI) Lab , Imperial College London
January 2023: "On the Synergies of Causality and DeepLearning", Neuroscience in ML Seminar, ETH Zurich
April 2022: "Learning Neural Causal Models with Active Interventions", XAI seminar series, Imperial College London
October 2021: "Learning Neural Causal Models with Active Interventions", Causality Reading Group, TU Darmstadt