no code implementations • ICML 2018 • Hadi Daneshmand, Jonas Kohler, Aurelien Lucchi, Thomas Hofmann
We analyze the variance of stochastic gradients along negative curvature directions in certain non-convex machine learning models and show that stochastic gradients exhibit a strong component along these directions.
no code implementations • 27 May 2018 • Jonas Kohler, Hadi Daneshmand, Aurelien Lucchi, Ming Zhou, Klaus Neymeyr, Thomas Hofmann
Normalization techniques such as Batch Normalization have been applied successfully for training deep neural networks.
no code implementations • 22 May 2019 • Jonas Kohler, Leonard Adolphs, Aurelien Lucchi
We investigate the use of regularized Newton methods with adaptive norms for optimizing neural networks.
no code implementations • 2 Jul 2019 • Antonio Orvieto, Jonas Kohler, Aurelien Lucchi
We first derive a general continuous-time model that can incorporate arbitrary types of memory, for both deterministic and stochastic settings.
no code implementations • 25 Sep 2019 • Leonard Adolphs, Jonas Kohler, Aurelien Lucchi
We investigate the use of ellipsoidal trust region constraints for second-order optimization of neural networks.
no code implementations • 23 Nov 2019 • Aurelien Lucchi, Jonas Kohler
We present a stochastic optimization method that uses a fourth-order regularized model to find local minima of smooth and potentially non-convex objective functions with a finite-sum structure.
no code implementations • 3 Mar 2020 • Hadi Daneshmand, Jonas Kohler, Francis Bach, Thomas Hofmann, Aurelien Lucchi
Randomly initialized neural networks are known to become harder to train with increasing depth, unless architectural enhancements like residual connections and batch normalization are used.
no code implementations • 1 Nov 2020 • Nikolaos Tselepidis, Jonas Kohler, Antonio Orvieto
In the context of deep learning, many optimization methods use gradient covariance information in order to accelerate the convergence of Stochastic Gradient Descent.
no code implementations • NeurIPS 2020 • Hadi Daneshmand, Jonas Kohler, Francis Bach, Thomas Hofmann, Aurelien Lucchi
Randomly initialized neural networks are known to become harder to train with increasing depth, unless architectural enhancements like residual connections and batch normalization are used.
1 code implementation • ICCV 2021 • Dario Pavllo, Jonas Kohler, Thomas Hofmann, Aurelien Lucchi
Recent advances in differentiable rendering have sparked an interest in learning generative models of textured 3D meshes from image collections.
1 code implementation • 5 May 2021 • Adrian Hoffmann, Claudio Fanconi, Rahul Rade, Jonas Kohler
Deep neural networks that yield human interpretable decisions by architectural design have lately become an increasingly popular alternative to post hoc interpretation of traditional black-box models.
no code implementations • 7 Jun 2021 • Antonio Orvieto, Jonas Kohler, Dario Pavllo, Thomas Hofmann, Aurelien Lucchi
This paper revisits the so-called vanishing gradient phenomenon, which commonly occurs in deep randomly initialized neural networks.
1 code implementation • 9 Aug 2021 • Ziyad Sheebaelhamd, Konstantinos Zisis, Athina Nisioti, Dimitris Gkouletsos, Dario Pavllo, Jonas Kohler
Multi-agent control problems constitute an interesting area of application for deep reinforcement learning models with continuous action spaces.
1 code implementation • 2 Nov 2021 • Jonas Kohler, Maarten C. Ottenhoff, Sophocles Goulis, Miguel Angrick, Albert J. Colon, Louis Wagner, Simon Tousseyn, Pieter L. Kubben, Christian Herff
Speech Neuroprostheses have the potential to enable communication for people with dysarthria or anarthria.
no code implementations • 6 Dec 2023 • Felix Wimbauer, Bichen Wu, Edgar Schoenfeld, Xiaoliang Dai, Ji Hou, Zijian He, Artsiom Sanakoyeu, Peizhao Zhang, Sam Tsai, Jonas Kohler, Christian Rupprecht, Daniel Cremers, Peter Vajda, Jialiang Wang
However, one of the major drawbacks of diffusion models is that the image generation process is costly.
1 code implementation • 19 Dec 2023 • Angela Castillo, Jonas Kohler, Juan C. Pérez, Juan Pablo Pérez, Albert Pumarola, Bernard Ghanem, Pablo Arbeláez, Ali Thabet
Our findings provide insights into the efficiency of the conditional denoising process that contribute to more practical and swift deployment of text-conditioned diffusion models.
no code implementations • 26 Dec 2023 • Jonas Kohler, Nicolas Griffiths Sanchez, Luca Cavalli, Catherine Herold, Albert Pumarola, Alberto Garcia Garcia, Ali Thabet
In this study, we propose two novel input processing paradigms for novel view synthesis (NVS) methods based on layered scene representations that significantly improve their runtime without compromising quality.