Search Results for author:
Found 32 papers, 17 papers with code
PairBench: A Systematic Framework for Selecting Reliable Judge VLMs
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
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.
ReTreever: Tree-based Coarse-to-Fine Representations for Retrieval
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.
Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones
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
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.
Sample Compression Unleashed: New Generalization Bounds for Real Valued Losses
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.
InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation
We also compare the performance of open- and closed-source LLMs and various evaluation strategies.
RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content
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.
XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference
Just-in-time processing of a context is inefficient due to the quadratic cost of self-attention operations, and caching is desirable.
Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures
In statistical learning theory, a generalization bound usually involves a complexity measure imposed by the considered theoretical framework.
Capture the Flag: Uncovering Data Insights with Large Language Models
The extraction of a small number of relevant insights from vast amounts of data is a crucial component of data-driven decision-making.
Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
Over the past years, foundation models have caused a paradigm shift in machine learning due to their unprecedented capabilities for zero-shot and few-shot generalization.
TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series
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.
Causal Discovery with Language Models as Imperfect Experts
Understanding the causal relationships that underlie a system is a fundamental prerequisite to accurate decision-making.
Regions of Reliability in the Evaluation of Multivariate Probabilistic Forecasts
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.
DAG Learning on the Permutahedron
We propose a continuous optimization framework for discovering a latent directed acyclic graph (DAG) from observational data.
Learning Discrete Directed Acyclic Graphs via Backpropagation
Recently continuous relaxations have been proposed in order to learn Directed Acyclic Graphs (DAGs) from data by backpropagation, instead of using combinatorial optimization.
On Margins and Generalisation for Voting Classifiers
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
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.
Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound
We investigate a stochastic counterpart of majority votes over finite ensembles of classifiers, and study its generalization properties.
RainBench: Towards Global Precipitation Forecasting from Satellite Imagery
Extreme precipitation events, such as violent rainfall and hail storms, routinely ravage economies and livelihoods around the developing world.
Learning Binary Decision Trees by Argmin Differentiation
We address the problem of learning binary decision trees that partition data for some downstream task.
Learning Binary Trees via Sparse Relaxation
In this work we derive a novel sparse relaxation for binary tree learning.
Cumulo: A Dataset for Learning Cloud Classes
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
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
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
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.
Efficient Defenses Against Adversarial Attacks
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
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.
beta-risk: a New Surrogate Risk for Learning from Weakly Labeled Data
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
Over the past ten years, metric learning allowed the improvement of the numerous machine learning approaches that manipulate distances or similarities.
Lipschitz Continuity of Mahalanobis Distances and Bilinear Forms
Many theoretical results in the machine learning domain stand only for functions that are Lipschitz continuous.
