Search Results for author:
Found 32 papers, 15 papers with code
Constructing Variables Using Classifiers as an Aid to Regression: An Empirical Assessment
This paper proposes a method for the automatic creation of variables (in the case of regression) that complement the information contained in the initial input vector.
An analysis of the noise schedule for score-based generative models
Under mild assumptions on the data distribution, we establish an upper bound for the KL divergence between the target and the estimated distributions, explicitly depending on any time-dependent noise schedule.
A Practical Approach to Novel Class Discovery in Tabular Data
In particular, the number of novel classes is usually assumed to be known in advance, and their labels are sometimes used to tune hyperparameters.
Evidential uncertainties on rich labels for active learning
Recent research in active learning, and more precisely in uncertainty sampling, has focused on the decomposition of model uncertainty into reducible and irreducible uncertainties.
Human Activity Segmentation Challenge @ ECML/PKDD’23
Despite its importance, existing methods demonstrate limited efficacy on real-world multivariate time series data.
Viewing the process of generating counterfactuals as a source of knowledge: a new approach for explaining classifiers
There are now many explainable AI methods for understanding the decisions of a machine learning model.
Biquality Learning: a Framework to Design Algorithms Dealing with Closed-Set Distribution Shifts
Training machine learning models from data with weak supervision and dataset shifts is still challenging.
biquality-learn: a Python library for Biquality Learning
That is why Biquality Learning has been proposed as a machine learning framework to design algorithms capable of handling multiple weaknesses of supervision and dataset shifts without assumptions on their nature and level by relying on the availability of a small trusted dataset composed of cleanly labeled and representative samples.
Automatic Feature Engineering for Time Series Classification: Evaluation and Discussion
Time Series Classification (TSC) has received much attention in the past two decades and is still a crucial and challenging problem in data science and knowledge engineering.
An Efficient Shapley Value Computation for the Naive Bayes Classifier
In the case of the naive Bayes classifier, and to our knowledge, there is no ``analytical" formulation of Shapley values.
An Interactive Interface for Novel Class Discovery in Tabular Data
This task is difficult and can often only be performed by a domain expert.
Swing contract pricing: with and without Neural Networks
We propose two parametric approaches to evaluate swing contracts with firm constraints.
Efficient simulation of individual-based population models: the R Package IBMPopSim
The R Package IBMPopSim aims to simulate the random evolution of heterogeneous populations using stochastic Individual-Based Models (IBMs).
Novel Class Discovery: an Introduction and Key Concepts
We then give an overview of the different families of approaches, organized by the way they transfer knowledge from the labeled set to the unlabeled set.
Découvrir de nouvelles classes dans des données tabulaires
In Novel Class Discovery (NCD), the goal is to find new classes in an unlabeled set given a labeled set of known but different classes.
A Method for Discovering Novel Classes in Tabular Data
In this paper, we propose TabularNCD, a new method for discovering novel classes in tabular data.
Open challenges for Machine Learning based Early Decision-Making research
However, the later a decision is made, the more its accuracy tends to improve, since the description of the problem to hand is enriched over time.
When to Classify Events in Open Times Series?
In the Early Classification in Open Time Series problem (ECOTS), the task is to predict events, i. e. their class and time interval, at the moment that optimizes the accuracy vs. earliness trade-off.
Construction de variables a l'aide de classifieurs comme aide a la regression
This paper proposes a method for the automatic creation of variables (in the case of regression) that complement the information contained in the initial input vector.
Early and Revocable Time Series Classification
Many approaches have been proposed for early classification of time series in light of itssignificance in a wide range of applications including healthcare, transportation and fi-nance.
Contrastive Representations for Label Noise Require Fine-Tuning
In presence of noise the experiments show that fine tuning of Contrastive representation allows the six methods to achieve better results than end-to-end learning and represent a new reference compare to the recent state of art.
Early Classification of Time Series is Meaningful
Many approaches have been proposed for early classification of time series in light of its significance in a wide range of applications including healthcare, transportation and finance.
Interpretable Feature Construction for Time Series Extrinsic Regression
Supervised learning of time series data has been extensively studied for the case of a categorical target variable.
Predictive K-means with local models
We present two new algorithms using this technique and show on a variety of data sets that they are competitive for prediction performance with pure supervised classifiers while offering interpretability of the clusters discovered.
Learning active learning at the crossroads? evaluation and discussion
To this end, we present the results of a benchmark performed on 20 datasets that compares a strategy learned using a recent meta-learning algorithm with margin sampling.
From Weakly Supervised Learning to Biquality Learning: an Introduction
The field of Weakly Supervised Learning (WSL) has recently seen a surge of popularity, with numerous papers addressing different types of "supervision deficiencies".
On the intrinsic robustness to noise of some leading classifiers and symmetric loss function -- an empirical evaluation
In some industrial applications such as fraud detection, the performance of common supervision techniques may be affected by the poor quality of the available labels : in actual operational use-cases, these labels may be weak in quantity, quality or trustworthiness.
Importance Reweighting for Biquality Learning
The field of Weakly Supervised Learning (WSL) has recently seen a surge of popularity, with numerous papers addressing different types of "supervision deficiencies", namely: poor quality, non adaptability, and insufficient quantity of labels.
Quantization-based Bermudan option pricing in the $FX$ world
This paper proposes two numerical solution based on Product Optimal Quantization for the pricing of Foreign Echange (FX) linked long term Bermudan options e. g. Bermudan Power Reverse Dual Currency options, where we take into account stochastic domestic and foreign interest rates on top of stochastic FX rate, hence we consider a 3-factor model.
Graph2Bots, Unsupervised Assistance for Designing Chatbots
We present Graph2Bots, a tool for assisting conversational agent designers.
Should we Reload Time Series Classification Performance Evaluation ? (a position paper)
Since the introduction and the public availability of the \textsc{ucr} time series benchmark data sets, numerous Time Series Classification (TSC) methods has been designed, evaluated and compared to each others.
Day-ahead time series forecasting: application to capacity planning
In the context of capacity planning, forecasting the evolution of informatics servers usage enables companies to better manage their computational resources.
