Search Results for author: Valentina Zantedeschi

Found 32 papers, 17 papers with code

PairBench: A Systematic Framework for Selecting Reliable Judge VLMs

no code implementations21 Feb 2025 Aarash Feizi, Sai Rajeswar, Adriana Romero-Soriano, Reihaneh Rabbany, Spandana Gella, Valentina Zantedeschi, João Monteiro

As large vision language models (VLMs) are increasingly used as automated evaluators, understanding their ability to effectively compare data pairs as instructed in the prompt becomes essential.

Learning to Defer for Causal Discovery with Imperfect Experts

no code implementations18 Feb 2025 Oscar Clivio, Divyat Mahajan, Perouz Taslakian, Sara Magliacane, Ioannis Mitliagkas, Valentina Zantedeschi, Alexandre Drouin

Integrating expert knowledge, e. g. from large language models, into causal discovery algorithms can be challenging when the knowledge is not guaranteed to be correct.

Causal Discovery

ReTreever: Tree-based Coarse-to-Fine Representations for Retrieval

no code implementations11 Feb 2025 Shubham Gupta, Zichao Li, Tianyi Chen, Cem Subakan, Siva Reddy, Perouz Taslakian, Valentina Zantedeschi

In this paper, we propose a tree-based method for organizing and representing reference documents at various granular levels, which offers the flexibility to balance cost and utility, and eases the inspection of the corpus content and retrieval operations.

Answer Generation Question Answering +1

Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones

no code implementations26 Dec 2024 Mehrnaz Mofakhami, Reza Bayat, Ioannis Mitliagkas, Joao Monteiro, Valentina Zantedeschi

Early Exiting (EE) is a promising technique for speeding up inference by adaptively allocating compute resources to data points based on their difficulty.

Context is Key: A Benchmark for Forecasting with Essential Textual Information

1 code implementation24 Oct 2024 Andrew Robert Williams, Arjun Ashok, Étienne Marcotte, Valentina Zantedeschi, Jithendaraa Subramanian, Roland Riachi, James Requeima, Alexandre Lacoste, Irina Rish, Nicolas Chapados, Alexandre Drouin

To address this, we introduce "Context is Key" (CiK), a time series forecasting benchmark that pairs numerical data with diverse types of carefully crafted textual context, requiring models to integrate both modalities.

Decision Making Time Series +1

Sample Compression Unleashed: New Generalization Bounds for Real Valued Losses

1 code implementation26 Sep 2024 Mathieu Bazinet, Valentina Zantedeschi, Pascal Germain

The sample compression theory provides generalization guarantees for predictors that can be fully defined using a subset of the training dataset and a (short) message string, generally defined as a binary sequence.

Generalization Bounds valid

RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content

1 code implementation17 Jun 2024 Joao Monteiro, Pierre-Andre Noel, Etienne Marcotte, Sai Rajeswar, Valentina Zantedeschi, David Vazquez, Nicolas Chapados, Christopher Pal, Perouz Taslakian

We run a large-scale benchmark comprising several state-of-the-art LLMs to uncover differences in performance across models of various types and sizes in a context-conditional language modeling setting.

Benchmarking General Knowledge +3

Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures

1 code implementation19 Feb 2024 Paul Viallard, Rémi Emonet, Amaury Habrard, Emilie Morvant, Valentina Zantedeschi

In statistical learning theory, a generalization bound usually involves a complexity measure imposed by the considered theoretical framework.

Generalization Bounds Learning Theory

TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series

1 code implementation2 Oct 2023 Arjun Ashok, Étienne Marcotte, Valentina Zantedeschi, Nicolas Chapados, Alexandre Drouin

We introduce a new model for multivariate probabilistic time series prediction, designed to flexibly address a range of tasks including forecasting, interpolation, and their combinations.

Time Series Time Series Prediction

Causal Discovery with Language Models as Imperfect Experts

1 code implementation5 Jul 2023 Stephanie Long, Alexandre Piché, Valentina Zantedeschi, Tibor Schuster, Alexandre Drouin

Understanding the causal relationships that underlie a system is a fundamental prerequisite to accurate decision-making.

Causal Discovery Decision Making +3

Regions of Reliability in the Evaluation of Multivariate Probabilistic Forecasts

1 code implementation19 Apr 2023 Étienne Marcotte, Valentina Zantedeschi, Alexandre Drouin, Nicolas Chapados

Multivariate probabilistic time series forecasts are commonly evaluated via proper scoring rules, i. e., functions that are minimal in expectation for the ground-truth distribution.

scoring rule Time Series +1

DAG Learning on the Permutahedron

1 code implementation27 Jan 2023 Valentina Zantedeschi, Luca Franceschi, Jean Kaddour, Matt J. Kusner, Vlad Niculae

We propose a continuous optimization framework for discovering a latent directed acyclic graph (DAG) from observational data.

Learning Discrete Directed Acyclic Graphs via Backpropagation

no code implementations27 Oct 2022 Andrew J. Wren, Pasquale Minervini, Luca Franceschi, Valentina Zantedeschi

Recently continuous relaxations have been proposed in order to learn Directed Acyclic Graphs (DAGs) from data by backpropagation, instead of using combinatorial optimization.

Combinatorial Optimization

On Margins and Generalisation for Voting Classifiers

1 code implementation9 Jun 2022 Felix Biggs, Valentina Zantedeschi, Benjamin Guedj

We study the generalisation properties of majority voting on finite ensembles of classifiers, proving margin-based generalisation bounds via the PAC-Bayes theory.

Unsupervised Change Detection of Extreme Events Using ML On-Board

1 code implementation4 Nov 2021 Vít Růžička, Anna Vaughan, Daniele De Martini, James Fulton, Valentina Salvatelli, Chris Bridges, Gonzalo Mateo-Garcia, Valentina Zantedeschi

In this paper, we introduce RaVAEn, a lightweight, unsupervised approach for change detection in satellite data based on Variational Auto-Encoders (VAEs) with the specific purpose of on-board deployment.

Change Detection Management +2

Learning Binary Decision Trees by Argmin Differentiation

1 code implementation9 Oct 2020 Valentina Zantedeschi, Matt J. Kusner, Vlad Niculae

We address the problem of learning binary decision trees that partition data for some downstream task.

Clustering

Cumulo: A Dataset for Learning Cloud Classes

1 code implementation5 Nov 2019 Valentina Zantedeschi, Fabrizio Falasca, Alyson Douglas, Richard Strange, Matt J. Kusner, Duncan Watson-Parris

One of the greatest sources of uncertainty in future climate projections comes from limitations in modelling clouds and in understanding how different cloud types interact with the climate system.

Learning Landmark-Based Ensembles with Random Fourier Features and Gradient Boosting

no code implementations14 Jun 2019 Léo Gautheron, Pascal Germain, Amaury Habrard, Emilie Morvant, Marc Sebban, Valentina Zantedeschi

Unlike state-of-the-art Multiple Kernel Learning techniques that make use of a pre-computed dictionary of kernel functions to select from, at each iteration we fit a kernel by approximating it as a weighted sum of Random Fourier Features (RFF) and by optimizing their barycenter.

Fully Decentralized Joint Learning of Personalized Models and Collaboration Graphs

1 code implementation24 Jan 2019 Valentina Zantedeschi, Aurélien Bellet, Marc Tommasi

We consider the fully decentralized machine learning scenario where many users with personal datasets collaborate to learn models through local peer-to-peer exchanges, without a central coordinator.

Adversarial Robustness Toolbox v1.0.0

6 code implementations3 Jul 2018 Maria-Irina Nicolae, Mathieu Sinn, Minh Ngoc Tran, Beat Buesser, Ambrish Rawat, Martin Wistuba, Valentina Zantedeschi, Nathalie Baracaldo, Bryant Chen, Heiko Ludwig, Ian M. Molloy, Ben Edwards

Defending Machine Learning models involves certifying and verifying model robustness and model hardening with approaches such as pre-processing inputs, augmenting training data with adversarial samples, and leveraging runtime detection methods to flag any inputs that might have been modified by an adversary.

Adversarial Robustness BIG-bench Machine Learning +2

Efficient Defenses Against Adversarial Attacks

no code implementations21 Jul 2017 Valentina Zantedeschi, Maria-Irina Nicolae, Ambrish Rawat

Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat.

L$^3$-SVMs: Landmarks-based Linear Local Support Vectors Machines

no code implementations1 Mar 2017 Valentina Zantedeschi, Rémi Emonet, Marc Sebban

For their ability to capture non-linearities in the data and to scale to large training sets, local Support Vector Machines (SVMs) have received a special attention during the past decade.

Dimensionality Reduction

beta-risk: a New Surrogate Risk for Learning from Weakly Labeled Data

no code implementations NeurIPS 2016 Valentina Zantedeschi, Rémi Emonet, Marc Sebban

During the past few years, the machine learning community has paid attention to developping new methods for learning from weakly labeled data.

Metric Learning as Convex Combinations of Local Models With Generalization Guarantees

no code implementations CVPR 2016 Valentina Zantedeschi, Remi Emonet, Marc Sebban

Over the past ten years, metric learning allowed the improvement of the numerous machine learning approaches that manipulate distances or similarities.

Metric Learning regression

Lipschitz Continuity of Mahalanobis Distances and Bilinear Forms

no code implementations4 Apr 2016 Valentina Zantedeschi, Rémi Emonet, Marc Sebban

Many theoretical results in the machine learning domain stand only for functions that are Lipschitz continuous.

BIG-bench Machine Learning

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