Mathias Lechner

research

∙ 05/23/2023

On the Size and Approximation Error of Distilled Sets

Dataset Distillation is the task of synthesizing small datasets from lar...

0 Alaa Maalouf, et al. ∙

research

∙ 03/21/2023

Infrastructure-based End-to-End Learning and Prevention of Driver Failure

Intelligent intersection managers can improve safety by detecting danger...

0 Noam Buckman, et al. ∙

research

∙ 02/13/2023

Dataset Distillation with Convexified Implicit Gradients

We propose a new dataset distillation algorithm using reparameterization...

0 Noel Loo, et al. ∙

research

∙ 02/02/2023

Dataset Distillation Fixes Dataset Reconstruction Attacks

Modern deep learning requires large volumes of data, which could contain...

0 Noel Loo, et al. ∙

research

∙ 12/21/2022

Cooperative Flight Control Using Visual-Attention – Air-Guardian

The cooperation of a human pilot with an autonomous agent during flight ...

0 Lianhao Yin, et al. ∙

research

∙ 11/29/2022

Quantization-aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networks

We study the problem of training and certifying adversarially robust qua...

0 Mathias Lechner, et al. ∙

research

∙ 10/11/2022

Learning Control Policies for Stochastic Systems with Reach-avoid Guarantees

We study the problem of learning controllers for discrete-time non-linea...

0 Đorđe Žikelić, et al. ∙

research

∙ 10/11/2022

Learning Control Policies for Region Stabilization in Stochastic Systems

We consider the problem of learning control policies in stochastic syste...

0 Matin Ansaripour, et al. ∙

research

∙ 10/10/2022

PyHopper – Hyperparameter optimization

Hyperparameter tuning is a fundamental aspect of machine learning resear...

0 Mathias Lechner, et al. ∙

research

∙ 10/09/2022

Are All Vision Models Created Equal? A Study of the Open-Loop to Closed-Loop Causality Gap

There is an ever-growing zoo of modern neural network models that can ef...

0 Mathias Lechner, et al. ∙

research

∙ 09/26/2022

Liquid Structural State-Space Models

A proper parametrization of state transition matrices of linear state-sp...

6 Ramin Hasani, et al. ∙

research

∙ 06/02/2022

Entangled Residual Mappings

Residual mappings have been shown to perform representation learning in ...

6 Mathias Lechner, et al. ∙

research

∙ 05/24/2022

Learning Stabilizing Policies in Stochastic Control Systems

In this work, we address the problem of learning provably stable neural ...

0 Đorđe Žikelić, et al. ∙

research

∙ 04/15/2022

Revisiting the Adversarial Robustness-Accuracy Tradeoff in Robot Learning

Adversarial training (i.e., training on adversarially perturbed input da...

3 Mathias Lechner, et al. ∙

research

∙ 12/17/2021

Stability Verification in Stochastic Control Systems via Neural Network Supermartingales

We consider the problem of formally verifying almost-sure (a.s.) asympto...

0 Mathias Lechner, et al. ∙

research

∙ 11/04/2021

Infinite Time Horizon Safety of Bayesian Neural Networks

Bayesian neural networks (BNNs) place distributions over the weights of ...

0 Mathias Lechner, et al. ∙

research

∙ 10/14/2021

Interactive Analysis of CNN Robustness

While convolutional neural networks (CNNs) have found wide adoption as s...

21 Stefan Sietzen, et al. ∙

research

∙ 07/18/2021

GoTube: Scalable Stochastic Verification of Continuous-Depth Models

We introduce a new stochastic verification algorithm that formally quant...

11 Sophie A. Neubauer, et al. ∙

research

∙ 06/25/2021

Closed-form Continuous-Depth Models

Continuous-depth neural models, where the derivative of the model's hidd...

9 Ramin Hasani, et al. ∙

research

∙ 06/15/2021

Causal Navigation by Continuous-time Neural Networks

Imitation learning enables high-fidelity, vision-based learning of polic...

1 Charles Vorbach, et al. ∙

research

∙ 06/13/2021

On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification

Robustness to variations in lighting conditions is a key objective for a...

13 Zahra Babaiee, et al. ∙

research

∙ 03/15/2021

Adversarial Training is Not Ready for Robot Learning

Adversarial training is an effective method to train deep learning model...

9 Mathias Lechner, et al. ∙

research

∙ 03/08/2021

Model-based versus Model-free Deep Reinforcement Learning for Autonomous Racing Cars

Despite the rich theoretical foundation of model-based deep reinforcemen...

20 Axel Brunnbauer, et al. ∙

research

∙ 12/16/2020

On The Verification of Neural ODEs with Stochastic Guarantees

We show that Neural ODEs, an emerging class of time-continuous neural ne...

13 Sophie A. Neubauer, et al. ∙

research

∙ 12/15/2020

Scalable Verification of Quantized Neural Networks (Technical Report)

Formal verification of neural networks is an active topic of research, a...

0 Thomas A. Henzinger, et al. ∙

research

∙ 12/14/2020

Lagrangian Reachtubes: The Next Generation

We introduce LRT-NG, a set of techniques and an associated toolset that ...

5 Sophie A. Neubauer, et al. ∙

research

∙ 06/08/2020

Liquid Time-constant Networks

We introduce a new class of time-continuous recurrent neural network mod...

15 Ramin Hasani, et al. ∙

research

∙ 06/08/2020

Learning Long-Term Dependencies in Irregularly-Sampled Time Series

Recurrent neural networks (RNNs) with continuous-time hidden states are ...

1 Mathias Lechner, et al. ∙

research

∙ 11/01/2018

Liquid Time-constant Recurrent Neural Networks as Universal Approximators

In this paper, we introduce the notion of liquid time-constant (LTC) rec...

4 Ramin M. Hasani, et al. ∙

research

∙ 09/11/2018

Re-purposing Compact Neuronal Circuit Policies to Govern Reinforcement Learning Tasks

We propose an effective method for creating interpretable control agents...

2 Ramin M. Hasani, et al. ∙

research

∙ 09/11/2018

Response Characterization for Auditing Cell Dynamics in Long Short-term Memory Networks

In this paper, we introduce a novel method to interpret recurrent neural...

2 Ramin M. Hasani, et al. ∙

research

∙ 03/22/2018

Neuronal Circuit Policies

We propose an effective way to create interpretable control agents, by r...

0 Mathias Lechner, et al. ∙

research

∙ 11/09/2017

Worm-level Control through Search-based Reinforcement Learning

Through natural evolution, nervous systems of organisms formed near-opti...

0 Mathias Lechner, et al. ∙

Mathias Lechner

Featured Co-authors