Search Results for author: Alexandros Kalousis

Found 31 papers, 9 papers with code

Permutation Equivariant Generative Adversarial Networks for Graphs

no code implementations7 Dec 2021 Yoann Boget, Magda Gregorova, Alexandros Kalousis

One solution consists of using equivariant generative functions, which ensure the ordering invariance.

Optimality Inductive Biases and Agnostic Guidelines for Offline Reinforcement Learning

1 code implementation3 Jul 2021 Lionel Blondé, Alexandros Kalousis, Stéphane Marchand-Maillet

Only our framework allowed us to design a method that performed well across the spectrum while remaining modular if more information about the quality of the data ever becomes available.

Inductive Bias Offline RL +1

Conditional Neural Relational Inference for Interacting Systems

2 code implementations21 Jun 2021 Joao A. Candido Ramos, Lionel Blondé, Stéphane Armand, Alexandros Kalousis

In this work, we want to learn to model the dynamics of similar yet distinct groups of interacting objects.

Learned transform compression with optimized entropy encoding

1 code implementation ICLR Workshop Neural_Compression 2021 Magda Gregorová, Marc Desaules, Alexandros Kalousis

We consider the problem of learned transform compression where we learn both, the transform as well as the probability distribution over the discrete codes.

Quantization

Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling

no code implementations NeurIPS 2021 Naoya Takeishi, Alexandros Kalousis

A key technical challenge is to strike a balance between the incomplete physics and trainable components such as neural networks for ensuring that the physics part is used in a meaningful manner.

ProxyFAUG: Proximity-based Fingerprint Augmentation

no code implementations4 Feb 2021 Grigorios G. Anagnostopoulos, Alexandros Kalousis

The best performing published positioning method on this dataset is improved by 40% in terms of median error and 6% in terms of mean error, with the use of the augmented dataset.

Analysing the Data-Driven Approach of Dynamically Estimating Positioning Accuracy

no code implementations20 Nov 2020 Grigorios G. Anagnostopoulos, Alexandros Kalousis

More specifically, with the use of a public LoRaWAN dataset, the current work analyses: the repartition of the available training set between the tasks of determining the location estimates and the DAE, the concept of selecting a subset of the most reliable estimates, and the impact that the spatial distribution of the data has to the accuracy of the DAE.

Goal-directed Generation of Discrete Structures with Conditional Generative Models

no code implementations NeurIPS 2020 Amina Mollaysa, Brooks Paige, Alexandros Kalousis

Unfortunately, maximum likelihood training of such models often fails with the samples from the generative model inadequately respecting the input properties.

Program Synthesis reinforcement-learning

Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning

1 code implementation28 Jun 2020 Lionel Blondé, Pablo Strasser, Alexandros Kalousis

Despite the recent success of reinforcement learning in various domains, these approaches remain, for the most part, deterringly sensitive to hyper-parameters and are often riddled with essential engineering feats allowing their success.

Continuous Control Imitation Learning

Improving VAE generations of multimodal data through data-dependent conditional priors

no code implementations25 Nov 2019 Frantzeska Lavda, Magda Gregorová, Alexandros Kalousis

We propose a novel formulation of variational autoencoders, conditional prior VAE (CP-VAE), which learns to differentiate between the individual mixture components and therefore allows for generations from the distributional data clusters.

A Reproducible Comparison of RSSI Fingerprinting Localization Methods Using LoRaWAN

no code implementations14 Aug 2019 Grigorios G. Anagnostopoulos, Alexandros Kalousis

The use of fingerprinting localization techniques in outdoor IoT settings has started to gain popularity over the recent years.

A Reproducible Analysis of RSSI Fingerprinting for Outdoor Localization Using Sigfox: Preprocessing and Hyperparameter Tuning

no code implementations14 Aug 2019 Grigorios G. Anagnostopoulos, Alexandros Kalousis

To facilitate the reproducibility of tests and comparability of results, the code and train/validation/test split used in this study are available.

Indoor Localization

Learning by stochastic serializations

no code implementations27 May 2019 Pablo Strasser, Stephane Armand, Stephane Marchand-Maillet, Alexandros Kalousis

In this paper, we propose to map any complex structure onto a generic form, called serialization, over which we can apply any sequence-based density estimator.

Variational Saccading: Efficient Inference for Large Resolution Images

1 code implementation8 Dec 2018 Jason Ramapuram, Maurits Diephuis, Frantzeska Lavda, Russ Webb, Alexandros Kalousis

Image classification with deep neural networks is typically restricted to images of small dimensionality such as 224 x 244 in Resnet models [24].

General Classification Image Classification +2

Continual Classification Learning Using Generative Models

no code implementations24 Oct 2018 Frantzeska Lavda, Jason Ramapuram, Magda Gregorova, Alexandros Kalousis

Continual learning is the ability to sequentially learn over time by accommodating knowledge while retaining previously learned experiences.

Classification Continual Learning +1

Sample-Efficient Imitation Learning via Generative Adversarial Nets

2 code implementations6 Sep 2018 Lionel Blondé, Alexandros Kalousis

GAIL is a recent successful imitation learning architecture that exploits the adversarial training procedure introduced in GANs.

Continuous Control Imitation Learning

Structured nonlinear variable selection

no code implementations16 May 2018 Magda Gregorová, Alexandros Kalousis, Stéphane Marchand-Maillet

We investigate structured sparsity methods for variable selection in regression problems where the target depends nonlinearly on the inputs.

Additive models Variable Selection

Forecasting and Granger Modelling with Non-linear Dynamical Dependencies

1 code implementation27 Jun 2017 Magda Gregorová, Alexandros Kalousis, Stéphane Marchand-Maillet

Traditional linear methods for forecasting multivariate time series are not able to satisfactorily model the non-linear dependencies that may exist in non-Gaussian series.

Time Series

Lifelong Generative Modeling

1 code implementation ICLR 2018 Jason Ramapuram, Magda Gregorova, Alexandros Kalousis

Lifelong learning is the problem of learning multiple consecutive tasks in a sequential manner, where knowledge gained from previous tasks is retained and used to aid future learning over the lifetime of the learner.

Transfer Learning

Regularising Non-linear Models Using Feature Side-information

no code implementations ICML 2017 Amina Mollaysa, Pablo Strasser, Alexandros Kalousis

In this paper, we propose a framework that allows for the incorporation of the feature side-information during the learning of very general model families to improve the prediction performance.

feature selection

Space-Time Local Embeddings

no code implementations NeurIPS 2015 Ke Sun, Jun Wang, Alexandros Kalousis, Stephane Marchand-Maillet

We give theoretical propositions to show that space-time is a more powerful representation than Euclidean space.

Dimensionality Reduction

Factorizing LambdaMART for cold start recommendations

no code implementations4 Nov 2015 Phong Nguyen, Jun Wang, Alexandros Kalousis

Motivated by the fact that very often the users' and items' descriptions as well as the preference behavior can be well summarized by a small number of hidden factors, we propose a novel algorithm, LambdaMART Matrix Factorization (LambdaMART-MF), that learns a low rank latent representation of users and items using gradient boosted trees.

Learning-To-Rank Matrix Completion +1

Learning Leading Indicators for Time Series Predictions

no code implementations7 Jul 2015 Magda Gregorova, Alexandros Kalousis, Stéphane Marchand-Maillet

We consider the problem of learning models for forecasting multiple time-series systems together with discovering the leading indicators that serve as good predictors for the system.

Time Series

Two-Stage Metric Learning

no code implementations12 May 2014 Jun Wang, Ke Sun, Fei Sha, Stephane Marchand-Maillet, Alexandros Kalousis

This induces in the input data space a new family of distance metric with unique properties.

Metric Learning

A Metric-learning based framework for Support Vector Machines and Multiple Kernel Learning

no code implementations16 Sep 2013 Huyen Do, Alexandros Kalousis

Recently, SVMs have been analyzed from SVM and metric learning, and to develop new algorithms that build on the strengths of each.

Metric Learning

Parametric Local Metric Learning for Nearest Neighbor Classification

no code implementations NeurIPS 2012 Jun Wang, Alexandros Kalousis, Adam Woznica

We present a new parametric local metric learning method in which we learn a smooth metric matrix function over the data manifold.

Classification General Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.