Alessandro Leite

Audrey Poinsot, Alessandro Leite

Data augmentation is essential when applying Machine Learning in small-data regimes. It generates new samples following the observed data distribution while increasing their diversity and variability to help researchers and practitioners improve their models' robustness and, thus, deploy them in the real world. Nevertheless, its usage in tabular data still needs to be improved, as prior knowledge about the underlying data mechanism is seldom considered, limiting the fidelity and diversity of the generated data. Causal data augmentation strategies have been pointed out as a solution to handle these challenges by relying on conditional independence encoded in a causal graph. In this context, this paper experimentally analyzed the ADMG causal augmentation method considering different settings to support researchers and practitioners in understanding under which conditions prior knowledge helps generate new data points and, consequently, enhances the robustness of their models. The results highlighted that the studied method (a) is independent of the underlying model mechanism, (b) requires a minimal number of observations that may be challenging in a small-data regime to improve an ML model's accuracy, (c) propagates outliers to the augmented set degrading the performance of the model, and (d) is sensitive to its hyperparameter's value.

Echo Diyun LU, Charles Findling, Marianne Clausel et al.

Regime transitions routinely break stationarity in time series, making calibrated uncertainty as important as point accuracy. We study distribution-free uncertainty for regime-switching forecasting by coupling Deep Switching State Space Models with Adaptive Conformal Inference (ACI) and its aggregated variant (AgACI). We also introduce a unified conformal wrapper that sits atop strong sequence baselines including S4, MC-Dropout GRU, sparse Gaussian processes, and a change-point local model to produce online predictive bands with finite-sample marginal guarantees under nonstationarity and model misspecification. Across synthetic and real datasets, conformalized forecasters achieve near-nominal coverage with competitive accuracy and generally improved band efficiency.

Edgar Jaber, Vincent Blot, Nicolas Brunel et al.

Gaussian processes (GPs) are a Bayesian machine learning approach widely used to construct surrogate models for the uncertainty quantification of computer simulation codes in industrial applications. It provides both a mean predictor and an estimate of the posterior prediction variance, the latter being used to produce Bayesian credibility intervals. Interpreting these intervals relies on the Gaussianity of the simulation model as well as the well-specification of the priors which are not always appropriate. We propose to address this issue with the help of conformal prediction. In the present work, a method for building adaptive cross-conformal prediction intervals is proposed by weighting the non-conformity score with the posterior standard deviation of the GP. The resulting conformal prediction intervals exhibit a level of adaptivity akin to Bayesian credibility sets and display a significant correlation with the surrogate model local approximation error, while being free from the underlying model assumptions and having frequentist coverage guarantees. These estimators can thus be used for evaluating the quality of a GP surrogate model and can assist a decision-maker in the choice of the best prior for the specific application of the GP. The performance of the method is illustrated through a panel of numerical examples based on various reference databases. Moreover, the potential applicability of the method is demonstrated in the context of surrogate modeling of an expensive-to-evaluate simulator of the clogging phenomenon in steam generators of nuclear reactors.

Audrey Poinsot, Alessandro Leite, Nicolas Chesneau et al.

This paper provides a comprehensive review of deep structural causal models (DSCMs), particularly focusing on their ability to answer counterfactual queries using observational data within known causal structures. It delves into the characteristics of DSCMs by analyzing the hypotheses, guarantees, and applications inherent to the underlying deep learning components and structural causal models, fostering a finer understanding of their capabilities and limitations in addressing different counterfactual queries. Furthermore, it highlights the challenges and open questions in the field of deep structural causal modeling. It sets the stages for researchers to identify future work directions and for practitioners to get an overview in order to find out the most appropriate methods for their needs.

Mathurin Videau, Alessandro Leite, Marc Schoenauer et al.

Mixture-of-Experts (MoE) models have shown promising potential for parameter-efficient scaling across domains. However, their application to image classification remains limited, often requiring billion-scale datasets to be competitive. In this work, we explore the integration of MoE layers into image classification architectures using open datasets. We conduct a systematic analysis across different MoE configurations and model scales. We find that moderate parameter activation per sample provides the best trade-off between performance and efficiency. However, as the number of activated parameters increases, the benefits of MoE diminish. Our analysis yields several practical insights for vision MoE design. First, MoE layers most effectively strengthen tiny and mid-sized models, while gains taper off for large-capacity networks and do not redefine state-of-the-art ImageNet performance. Second, a Last-2 placement heuristic offers the most robust cross-architecture choice, with Every-2 slightly better for Vision Transform (ViT), and both remaining effective as data and model scale increase. Third, larger datasets (e.g., ImageNet-21k) allow more experts, up to 16, for ConvNeXt to be utilized effectively without changing placement, as increased data reduces overfitting and promotes broader expert specialization. Finally, a simple linear router performs best, suggesting that additional routing complexity yields no consistent benefit.

Mathurin Videau, Badr Youbi Idrissi, Alessandro Leite et al. · meta-ai

Tokenization imposes a fixed granularity on the input text, freezing how a language model operates on data and how far in the future it predicts. Byte Pair Encoding (BPE) and similar schemes split text once, build a static vocabulary, and leave the model stuck with that choice. We relax this rigidity by introducing an autoregressive U-Net that learns to embed its own tokens as it trains. The network reads raw bytes, pools them into words, then pairs of words, then up to 4 words, giving it a multi-scale view of the sequence. At deeper stages, the model must predict further into the future -- anticipating the next few words rather than the next byte -- so deeper stages focus on broader semantic patterns while earlier stages handle fine details. When carefully tuning and controlling pretraining compute, shallow hierarchies tie strong BPE baselines, and deeper hierarchies have a promising trend. Because tokenization now lives inside the model, the same system can handle character-level tasks and carry knowledge across low-resource languages.

Mathurin Videau, Alessandro Leite, Marc Schoenauer et al.

Recent advancements have highlighted that large language models (LLMs), when given a small set of task-specific examples, demonstrate remarkable proficiency, a capability that extends to complex reasoning tasks. In particular, the combination of few-shot learning with the chain-of-thought (CoT) approach has been pivotal in steering models towards more logically consistent conclusions. This paper explores the optimization of example selection for designing effective CoT pre-prompts and shows that the choice of the optimization algorithm, typically in favor of comparison-based methods such as evolutionary computation, significantly enhances efficacy and feasibility. Specifically, thanks to a limited exploitative and overfitted optimization, Evolutionary Pre-Prompt Optimization (EPPO) brings an improvement over the naive few-shot approach exceeding 10 absolute points in exact match scores on benchmark datasets such as GSM8k and MathQA. These gains are consistent across various contexts and are further amplified when integrated with self-consistency (SC)

Mathurin Videau, Mariia Zameshina, Alessandro Leite et al.

AfterLearnER (After Learning Evolutionary Retrofitting) consists in applying evolutionary optimization to refine fully trained machine learning models by optimizing a set of carefully chosen parameters or hyperparameters of the model, with respect to some actual, exact, and hence possibly non-differentiable error signal, performed on a subset of the standard validation set. The efficiency of AfterLearnER is demonstrated by tackling non-differentiable signals such as threshold-based criteria in depth sensing, the word error rate in speech re-synthesis, the number of kills per life at Doom, computational accuracy or BLEU in code translation, image quality in 3D generative adversarial networks (GANs), and user feedback in image generation via Latent Diffusion Models (LDM). This retrofitting can be done after training, or dynamically at inference time by taking into account the user feedback. The advantages of AfterLearnER are its versatility, the possibility to use non-differentiable feedback, including human evaluations (i.e., no gradient is needed), the limited overfitting supported by a theoretical study, and its anytime behavior. Last but not least, AfterLearnER requires only a small amount of feedback, i.e., a few dozen to a few hundred scalars, compared to the tens of thousands needed in most related published works.

Felipe Angelim, Alessandro Leite

We propose Partition Trees, a tree-based framework for conditional density estimation over general outcome spaces, supporting both continuous and categorical variables within a unified formulation. Our approach models conditional distributions as piecewise-constant densities on data adaptive partitions and learns trees by directly minimizing conditional negative log-likelihood. This yields a scalable, nonparametric alternative to existing probabilistic trees that does not make parametric assumptions about the target distribution. We further introduce Partition Forests, an ensemble extension obtained by averaging conditional densities. Empirically, we demonstrate improved probabilistic prediction over CART-style trees and competitive or superior performance compared to state-of-the-art probabilistic tree methods and Random Forests, along with robustness to redundant features and heteroscedastic noise.

Panayiotis Panayiotou, Audrey Poinsot, Alessandro Leite et al.

Causal machine learning (Causal ML) aims to answer "what if" questions using machine learning algorithms, making it a promising tool for high-stakes decision-making. Yet, empirical evaluation practices in Causal ML remain limited. Existing benchmarks often rely on a handful of hand-crafted or semi-synthetic datasets, leading to brittle, non-generalizable conclusions. To bridge this gap, we introduce CausalProfiler, a synthetic benchmark generator for Causal ML methods. Based on a set of explicit design choices about the class of causal models, queries, and data considered, the CausalProfiler randomly samples causal models, data, queries, and ground truths constituting the synthetic causal benchmarks. In this way, Causal ML methods can be rigorously and transparently evaluated under a variety of conditions. This work offers the first random generator of synthetic causal benchmarks with coverage guarantees and transparent assumptions operating on the three levels of causal reasoning: observation, intervention, and counterfactual. We demonstrate its utility by evaluating several state-of-the-art methods under diverse conditions and assumptions, both in and out of the identification regime, illustrating the types of analyses and insights the CausalProfiler enables.

Audrey Poinsot, Panayiotis Panayiotou, Alessandro Leite et al.

Causal machine learning has the potential to revolutionize decision-making by combining the predictive power of machine learning algorithms with the theory of causal inference. However, these methods remain underutilized by the broader machine learning community, in part because current empirical evaluations do not permit assessment of their reliability and robustness, undermining their practical utility. Specifically, one of the principal criticisms made by the community is the extensive use of synthetic experiments. We argue, on the contrary, that synthetic experiments are essential and necessary to precisely assess and understand the capabilities of causal machine learning methods. To substantiate our position, we critically review the current evaluation practices, spotlight their shortcomings, and propose a set of principles for conducting rigorous empirical analyses with synthetic data. Adopting the proposed principles will enable comprehensive evaluations that build trust in causal machine learning methods, driving their broader adoption and impactful real-world use.

Ismail Labiad, Mathurin Videau, Matthieu Kowalski et al.

Gradient-based optimization is the workhorse of deep learning, offering efficient and scalable training via backpropagation. However, exposing gradients during training can leak sensitive information about the underlying data, raising privacy and security concerns such as susceptibility to data poisoning attacks. In contrast, black box optimization methods, which treat the model as an opaque function, relying solely on function evaluations to guide optimization, offer a promising alternative in scenarios where data access is restricted, adversarial risks are high, or overfitting is a concern. This paper introduces BBoxER, an evolutionary black-box method for LLM post-training that induces an information bottleneck via implicit compression of the training data. Leveraging the tractability of information flow, we provide non-vacuous generalization bounds and strong theoretical guarantees for differential privacy, robustness to data poisoning attacks, and extraction attacks. In experiments with LLMs, we demonstrate empirically that black-box optimization methods-despite the scalability and computational challenges inherent to black-box approaches-are able to learn, showing how a few iterations of BBoxER improve performance, generalize well on a benchmark of reasoning datasets, and are robust to membership inference attacks. This positions BBoxER as an attractive add-on on top of gradient-based optimization, offering suitability for deployment in restricted or privacy-sensitive environments while also providing non-vacuous generalization guarantees.