Karol Arndt

Researcher, Nomagic

Joined

August 2022

Names

Karol Arndt (Preferred)

Emails

****@aalto.fi (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Google Scholar

Career & Education History

Researcher

Nomagic (nomagic.ai)

2024 – Present

PhD student

School of Electrical Engineering, Aalto University (aalto.fi)

2018 – 2023

Advisors, Relations & Conflicts

PhD Advisor

Ville Kyrki

2018 – 2023

Expertise

Computer vision

2018 – Present

Robot learning

2017 – Present

Reinforcement learning

2017 – 2023

Publications

From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transport
Quentin Bouniot, Ievgen Redko, Anton Mallasto, Charlotte Laclau, Oliver Struckmeier, Karol Arndt, Markus Heinonen, Ville Kyrki, Samuel Kaski
- MIV at CVPR 2025 (Non-proceedings Track) Poster
- Readers: Everyone
From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transport
Quentin Bouniot, Ievgen Redko, Anton Mallasto, Charlotte Laclau, Oliver Struckmeier, Karol Arndt, Markus Heinonen, Ville Kyrki, Samuel Kaski
- ICML 2024 MI Workshop Poster
- Readers: Everyone
From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transport
Quentin Bouniot, Ievgen Redko, Anton Mallasto, Charlotte Laclau, Oliver Struckmeier, Karol Arndt, Markus Heinonen, Ville Kyrki, Samuel Kaski
- Submitted to NeurIPS 2024
- Readers: Everyone
Understanding deep neural networks through the lens of their non-linearity
Quentin Bouniot, Ievgen Redko, Anton Mallasto, Charlotte Laclau, Oliver Struckmeier, Karol Arndt, Markus Heinonen, Ville Kyrki, Samuel Kaski
- Submitted to ICLR 2024
- Readers: Everyone
Learning representations that are closed-form Monge mapping optimal with application to domain adaptation
Oliver Struckmeier, Ievgen Redko, Anton Mallasto, Karol Arndt, Markus Heinonen, Ville Kyrki
- Accepted by TMLR
- Readers: Everyone
Co-Imitation: Learning Design and Behaviour by Imitation
Chang Rajani, Karol Arndt, David Blanco-Mulero, Kevin Sebastian Luck, Ville Kyrki
- 08 Oct 2022 (modified: 05 May 2023)
- Deep RL Workshop 2022
- Readers: Everyone

Karol Arndt

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transport

From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transport

From Alexnet to Transformers: Measuring the Non-linearity of Deep Neural Networks with Affine Optimal Transport

Understanding deep neural networks through the lens of their non-linearity

Learning representations that are closed-form Monge mapping optimal with application to domain adaptation

Co-Imitation: Learning Design and Behaviour by Imitation

Co-Authors