no code implementations • 2 Dec 2023 • Eduardo Pignatelli, Johan Ferret, Matthieu Geist, Thomas Mesnard, Hado van Hasselt, Laura Toni
In this survey, we review the state of the art of Temporal Credit Assignment (CA) in deep RL.
1 code implementation • 19 Jul 2023 • Pedro Gomes, Silvia Rossi, Laura Toni
From this understanding, we propose an improved architecture for point cloud prediction of deformable 3D objects.
no code implementations • 7 Jul 2023 • Laura Toni, Pascal Frossard
To achieve sample efficiency, we describe the network processes with an adaptive graph dictionary model, which typically leads to sparse spectral representations.
1 code implementation • 17 Feb 2023 • Clement Vignac, Nagham Osman, Laura Toni, Pascal Frossard
This work introduces MiDi, a novel diffusion model for jointly generating molecular graphs and their corresponding 3D arrangement of atoms.
no code implementations • 2 Oct 2022 • Gholamali Aminian, Saeed Masiha, Laura Toni, Miguel R. D. Rodrigues
Additionally, we demonstrate how our auxiliary distribution method can be used to derive the upper bounds on excess risk of some learning algorithms in the supervised learning context {\blue and the generalization error under the distribution mismatch scenario in supervised learning algorithms, where the distribution mismatch is modeled as $\alpha$-Jensen-Shannon or $\alpha$-R\'enyi divergence between the distribution of test and training data samples distributions.}
no code implementations • 15 Sep 2022 • Gholamali Aminian, Armin Behnamnia, Roberto Vega, Laura Toni, Chengchun Shi, Hamid R. Rabiee, Omar Rivasplata, Miguel R. D. Rodrigues
We propose learning methods for problems where feedback is missing for some samples, so there are samples with feedback and samples missing-feedback in the logged data.
no code implementations • 24 Feb 2022 • Gholamali Aminian, Mahed Abroshan, Mohammad Mahdi Khalili, Laura Toni, Miguel R. D. Rodrigues
A common assumption in semi-supervised learning is that the labeled, unlabeled, and test data are drawn from the same distribution.
no code implementations • NeurIPS 2021 • Gholamali Aminian, Yuheng Bu, Laura Toni, Miguel Rodrigues, Gregory Wornell
Various approaches have been developed to upper bound the generalization error of a supervised learning algorithm.
no code implementations • 2 Nov 2021 • Yuheng Bu, Gholamali Aminian, Laura Toni, Miguel Rodrigues, Gregory Wornell
We provide an information-theoretic analysis of the generalization ability of Gibbs-based transfer learning algorithms by focusing on two popular transfer learning approaches, $\alpha$-weighted-ERM and two-stage-ERM.
no code implementations • 28 Jul 2021 • Gholamali Aminian, Yuheng Bu, Laura Toni, Miguel R. D. Rodrigues, Gregory Wornell
As a result, they may fail to characterize the exact generalization ability of a learning algorithm.
no code implementations • ICML Workshop URL 2021 • Sephora Madjiheurem, Laura Toni
A major challenge in reinforcement learning is the design of agents that are able to generalize across tasks that share common dynamics.
1 code implementation • 15 Feb 2021 • Pedro Gomes, Silvia Rossi, Laura Toni
In this paper, we propose an end-to-end learning network to predict future frames in a point cloud sequence.
no code implementations • 3 Feb 2021 • Gholamali Aminian, Laura Toni, Miguel R. D. Rodrigues
Generalization error bounds are critical to understanding the performance of machine learning models.
no code implementations • 23 Oct 2020 • Gholamali Aminian, Laura Toni, Miguel R. D. Rodrigues
Generalization error bounds are critical to understanding the performance of machine learning models.
no code implementations • 31 Jul 2020 • Xiaowen Dong, Dorina Thanou, Laura Toni, Michael Bronstein, Pascal Frossard
The effective representation, processing, analysis, and visualization of large-scale structured data, especially those related to complex domains such as networks and graphs, are one of the key questions in modern machine learning.
no code implementations • 4 Jun 2020 • Kaige Yang, Laura Toni
Theoretically, we show that the proposed algorithm achieves a $\tilde{\mathcal{O}}(\hat{\beta}\sqrt{dT})$ upper bound of $T$-round regret, where $d$ is the dimension of arm features and $\hat{\beta}$ is the learned size of confidence bound.
no code implementations • 22 Oct 2019 • Sephora Madjiheurem, Laura Toni
In this paper, we propose state2vec, an efficient and low-complexity framework for learning successor features which (i) generalize across policies, (ii) ensure sample-efficiency during meta-test.
no code implementations • 12 Jul 2019 • Kaige Yang, Xiaowen Dong, Laura Toni
In terms of network regret (sum of cumulative regret over $n$ users), the proposed algorithm leads to a scaling as $\tilde{\mathcal{O}}(\Psi d\sqrt{nT})$, which is a significant improvement over $\tilde{\mathcal{O}}(nd\sqrt{T})$ in the state-of-the-art algorithm \algo{Gob. Lin} \Ccite{cesa2013gang}.
no code implementations • 11 Feb 2019 • Kaige Yang, Xiaowen Dong, Laura Toni
We provide a theoretical analysis of the representation learning problem aimed at learning the latent variables (design matrix) $\Theta$ of observations $Y$ with the knowledge of the coefficient matrix $X$.
no code implementations • 16 Jan 2019 • Sephora Madjiheurem, Laura Toni
In this work, we study value function approximation in reinforcement learning (RL) problems with high dimensional state or action spaces via a generalized version of representation policy iteration (RPI).
no code implementations • 31 Jul 2018 • Kaige Yang, Laura Toni
In this work, we study recommendation systems modelled as contextual multi-armed bandit (MAB) problems.