arXiv subjects

Léon Bottou

Publications and source records attributed to Léon Bottou.

At least 19 recordsLinked to original sources

arXiv2026

These Are Not All the Features You Are Looking For: A Fundamental Bottleneck in Supervised Pretraining

Transfer learning is widely used to adapt large pretrained models to new tasks with only a small amount of new data. However, a challenge persists -- the features from the original task often do not fully cover what is needed for unseen data, especially when the relatedness of tasks is not clear. Since deep learning models tend to learn very sparse representations, they retain only the minimal features required for the initial training while discarding potentially ones for downstream transfer. A theoretical framework developed in this work demonstrates that such pretraining captures inconsistent aspects of the data distribution, therefore, inducing transfer bias. To address this limitation, we propose an inexpensive ensembling strategy that aggregates multiple models to generate richer feature representations. On ResNet, this approach yields a $9\%$ improvement in transfer accuracy without incurring extra pretraining cost. We also present empirical evidence from a range of deep learning studies, confirming that the phenomenon is pervasive across modern deep learning architectures. These results suggests that relying solely on large pretrained networks is not always the most effective way to improve model generalization. Instead, fostering richer, more diverse representations -- e.g. - through model ensembles -- can substantially enhance transfer learning performance.

cs.LG↗

arXiv2026

Memory Mosaics at scale

Memory Mosaics [Zhang et al., 2025], networks of associative memories, have demonstrated appealing compositional and in-context learning capabilities on medium-scale networks (GPT-2 scale) and synthetic small datasets. This work shows that these favorable properties remain when we scale memory mosaics to large language model sizes (llama-8B scale) and real-world datasets. To this end, we scale memory mosaics to 10B size, we train them on one trillion tokens, we introduce a couple architectural modifications ("Memory Mosaics v2"), we assess their capabilities across three evaluation dimensions: training-knowledge storage, new-knowledge storage, and in-context learning. Throughout the evaluation, memory mosaics v2 match transformers on the learning of training knowledge (first dimension) and significantly outperforms transformers on carrying out new tasks at inference time (second and third dimensions). These improvements cannot be easily replicated by simply increasing the training data for transformers. A memory mosaics v2 trained on one trillion tokens still perform better on these tasks than a transformer trained on eight trillion tokens.

cs.AI↗

arXiv2025

A Single Character can Make or Break Your LLM Evals

Common Large Language model (LLM) evaluations rely on demonstration examples to steer models' responses to the desired style. While the number of examples used has been studied and standardized, the choice of how to format examples is less investigated. In evaluation protocols and real world usage, users face the choice how to separate in-context examples: use a comma? new line? semi-colon? hashtag? etc.? Surprisingly, we find this seemingly minor choice can dramatically alter model response quality. Across leading model families (Llama, Qwen, Gemma), performance on MMLU for example can vary by $\pm 23\%$ depending on the choice of delimiter. In fact, one can manipulate model rankings to put any model in the lead by only modifying the single character separating examples. We find LLMs' brittleness pervades topics, model families, and doesn't improve with scale. By probing attention head scores, we find that good-performing delimiters steer attention towards key tokens in the input. Finally, we explore methods to improve LLMs' robustness to the choice of delimiter. We find specifying the selected delimiter in the prompt boosts robustness and offer practical recommendations for the best-performing delimiters to select.

cs.CL↗

arXiv2025

Fine-tuning with Very Large Dropout

It is impossible today to pretend that the practice of machine learning is always compatible with the idea that training and testing data follow the same distribution. Several authors have recently used ensemble techniques to show how scenarios involving multiple data distributions are best served by representations that are both richer than those obtained by regularizing for the best in-distribution performance, and richer than those obtained under the influence of the implicit sparsity bias of common stochastic gradient procedures. This contribution investigates the use of very high dropout rates instead of ensembles to obtain such rich representations. Although training a deep network from scratch using such dropout rates is virtually impossible, fine-tuning a large pre-trained model under such conditions is not only possible but also achieves out-of-distribution performances that exceed those of both ensembles and weight averaging methods such as model soups. This result has practical significance because the importance of the fine-tuning scenario has considerably grown in recent years. This result also provides interesting insights on the nature of rich representations and on the intrinsically linear nature of fine-tuning a large network using a comparatively small dataset.

cs.LG↗

arXiv2025

Memory Mosaics

Memory Mosaics are networks of associative memories working in concert to achieve a prediction task of interest. Like transformers, memory mosaics possess compositional capabilities and in-context learning capabilities. Unlike transformers, memory mosaics achieve these capabilities in comparatively transparent way ("predictive disentanglement"). We illustrate these capabilities on a toy example and also show that memory mosaics perform as well or better than transformers on medium-scale language modeling tasks.

cs.LG↗

arXiv2023

Borges and AI

Many believe that Large Language Models (LLMs) open the era of Artificial Intelligence (AI). Some see opportunities while others see dangers. Yet both proponents and opponents grasp AI through the imagery popularised by science fiction. Will the machine become sentient and rebel against its creators? Will we experience a paperclip apocalypse? Before answering such questions, we should first ask whether this mental imagery provides a good description of the phenomenon at hand. Understanding weather patterns through the moods of the gods only goes so far. The present paper instead advocates understanding LLMs and their connection to AI through the imagery of Jorge Luis Borges, a master of 20th century literature, forerunner of magical realism, and precursor to postmodern literature. This exercise leads to a new perspective that illuminates the relation between language modelling and artificial intelligence.

cs.CL↗

arXiv2023

Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization

Foundation models are redefining how AI systems are built. Practitioners now follow a standard procedure to build their machine learning solutions: from a pre-trained foundation model, they fine-tune the weights on the target task of interest. So, the Internet is swarmed by a handful of foundation models fine-tuned on many diverse tasks: these individual fine-tunings exist in isolation without benefiting from each other. In our opinion, this is a missed opportunity, as these specialized models contain rich and diverse features. In this paper, we thus propose model ratatouille, a new strategy to recycle the multiple fine-tunings of the same foundation model on diverse auxiliary tasks. Specifically, we repurpose these auxiliary weights as initializations for multiple parallel fine-tunings on the target task; then, we average all fine-tuned weights to obtain the final model. This recycling strategy aims at maximizing the diversity in weights by leveraging the diversity in auxiliary tasks. Empirically, it improves the state of the art on the reference DomainBed benchmark for out-of-distribution generalization. Looking forward, this work contributes to the emerging paradigm of updatable machine learning where, akin to open-source software development, the community collaborates to reliably update machine learning models. Our code is released: https://github.com/facebookresearch/ModelRatatouille.

cs.LG↗

arXiv2023

Learning useful representations for shifting tasks and distributions

Does the dominant approach to learn representations (as a side effect of optimizing an expected cost for a single training distribution) remain a good approach when we are dealing with multiple distributions? Our thesis is that such scenarios are better served by representations that are richer than those obtained with a single optimization episode. We support this thesis with simple theoretical arguments and with experiments utilizing an apparently na\"ıve ensembling technique: concatenating the representations obtained from multiple training episodes using the same data, model, algorithm, and hyper-parameters, but different random seeds. These independently trained networks perform similarly. Yet, in a number of scenarios involving new distributions, the concatenated representation performs substantially better than an equivalently sized network trained with a single training run. This proves that the representations constructed by multiple training episodes are in fact different. Although their concatenation carries little additional information about the training task under the training distribution, it becomes substantially more informative when tasks or distributions change. Meanwhile, a single training episode is unlikely to yield such a redundant representation because the optimization process has no reason to accumulate features that do not incrementally improve the training performance.

cs.LG↗

arXiv2022

A Simple Convergence Proof of Adam and Adagrad

We provide a simple proof of convergence covering both the Adam and Adagrad adaptive optimization algorithms when applied to smooth (possibly non-convex) objective functions with bounded gradients. We show that in expectation, the squared norm of the objective gradient averaged over the trajectory has an upper-bound which is explicit in the constants of the problem, parameters of the optimizer, the dimension $d$, and the total number of iterations $N$. This bound can be made arbitrarily small, and with the right hyper-parameters, Adam can be shown to converge with the same rate of convergence $O(d\ln(N)/\sqrt{N})$. When used with the default parameters, Adam doesn't converge, however, and just like constant step-size SGD, it moves away from the initialization point faster than Adagrad, which might explain its practical success. Finally, we obtain the tightest dependency on the heavy ball momentum decay rate $β_1$ among all previous convergence bounds for non-convex Adam and Adagrad, improving from $O((1-β_1)^{-3})$ to $O((1-β_1)^{-1})$.

stat.ML↗

arXiv2022

Rich Feature Construction for the Optimization-Generalization Dilemma

There often is a dilemma between ease of optimization and robust out-of-distribution (OoD) generalization. For instance, many OoD methods rely on penalty terms whose optimization is challenging. They are either too strong to optimize reliably or too weak to achieve their goals. We propose to initialize the networks with a rich representation containing a palette of potentially useful features, ready to be used by even simple models. On the one hand, a rich representation provides a good initialization for the optimizer. On the other hand, it also provides an inductive bias that helps OoD generalization. Such a representation is constructed with the Rich Feature Construction (RFC) algorithm, also called the Bonsai algorithm, which consists of a succession of training episodes. During discovery episodes, we craft a multi-objective optimization criterion and its associated datasets in a manner that prevents the network from using the features constructed in the previous iterations. During synthesis episodes, we use knowledge distillation to force the network to simultaneously represent all the previously discovered features. Initializing the networks with Bonsai representations consistently helps six OoD methods achieve top performance on ColoredMNIST benchmark. The same technique substantially outperforms comparable results on the Wilds Camelyon17 task, eliminates the high result variance that plagues other methods, and makes hyperparameter tuning and model selection more reliable.

cs.LG↗

arXiv2021

Algorithmic Bias and Data Bias: Understanding the Relation between Distributionally Robust Optimization and Data Curation

Machine learning systems based on minimizing average error have been shown to perform inconsistently across notable subsets of the data, which is not exposed by a low average error for the entire dataset. In consequential social and economic applications, where data represent people, this can lead to discrimination of underrepresented gender and ethnic groups. Given the importance of bias mitigation in machine learning, the topic leads to contentious debates on how to ensure fairness in practice (data bias versus algorithmic bias). Distributionally Robust Optimization (DRO) seemingly addresses this problem by minimizing the worst expected risk across subpopulations. We establish theoretical results that clarify the relation between DRO and the optimization of the same loss averaged on an adequately weighted training dataset. The results cover finite and infinite number of training distributions, as well as convex and non-convex loss functions. We show that neither DRO nor curating the training set should be construed as a complete solution for bias mitigation: in the same way that there is no universally robust training set, there is no universal way to setup a DRO problem and ensure a socially acceptable set of results. We then leverage these insights to provide a mininal set of practical recommendations for addressing bias with DRO. Finally, we discuss ramifications of our results in other related applications of DRO, using an example of adversarial robustness. Our results show that there is merit to both the algorithm-focused and the data-focused side of the bias debate, as long as arguments in favor of these positions are precisely qualified and backed by relevant mathematics known today.

cs.LG↗

arXiv2021

Music Source Separation in the Waveform Domain

Source separation for music is the task of isolating contributions, or stems, from different instruments recorded individually and arranged together to form a song. Such components include voice, bass, drums and any other accompaniments.Contrarily to many audio synthesis tasks where the best performances are achieved by models that directly generate the waveform, the state-of-the-art in source separation for music is to compute masks on the magnitude spectrum. In this paper, we compare two waveform domain architectures. We first adapt Conv-Tasnet, initially developed for speech source separation,to the task of music source separation. While Conv-Tasnet beats many existing spectrogram-domain methods, it suffersfrom significant artifacts, as shown by human evaluations. We propose instead Demucs, a novel waveform-to-waveform model,with a U-Net structure and bidirectional LSTM.Experiments on the MusDB dataset show that, with proper data augmentation, Demucs beats allexisting state-of-the-art architectures, including Conv-Tasnet, with 6.3 SDR on average, (and up to 6.8 with 150 extra training songs, even surpassing the IRM oracle for the bass source).Using recent development in model quantization, Demucs can be compressed down to 120MBwithout any loss of accuracy.We also provide human evaluations, showing that Demucs benefit from a large advantagein terms of the naturalness of the audio. However, it suffers from some bleeding,especially between the vocals and other source.

cs.SD↗

arXiv2021

Beyond Folklore: A Scaling Calculus for the Design and Initialization of ReLU Networks

We propose a system for calculating a "scaling constant" for layers and weights of neural networks. We relate this scaling constant to two important quantities that relate to the optimizability of neural networks, and argue that a network that is "preconditioned" via scaling, in the sense that all weights have the same scaling constant, will be easier to train. This scaling calculus results in a number of consequences, among them the fact that the geometric mean of the fan-in and fan-out, rather than the fan-in, fan-out, or arithmetic mean, should be used for the initialization of the variance of weights in a neural network. Our system allows for the off-line design & engineering of ReLU neural networks, potentially replacing blind experimentation.

cs.LG↗

arXiv2020

WNGrad: Learn the Learning Rate in Gradient Descent

Adjusting the learning rate schedule in stochastic gradient methods is an important unresolved problem which requires tuning in practice. If certain parameters of the loss function such as smoothness or strong convexity constants are known, theoretical learning rate schedules can be applied. However, in practice, such parameters are not known, and the loss function of interest is not convex in any case. The recently proposed batch normalization reparametrization is widely adopted in most neural network architectures today because, among other advantages, it is robust to the choice of Lipschitz constant of the gradient in loss function, allowing one to set a large learning rate without worry. Inspired by batch normalization, we propose a general nonlinear update rule for the learning rate in batch and stochastic gradient descent so that the learning rate can be initialized at a high value, and is subsequently decreased according to gradient observations along the way. The proposed method is shown to achieve robustness to the relationship between the learning rate and the Lipschitz constant, and near-optimal convergence rates in both the batch and stochastic settings ($O(1/T)$ for smooth loss in the batch setting, and $O(1/\sqrt{T})$ for convex loss in the stochastic setting). We also show through numerical evidence that such robustness of the proposed method extends to highly nonconvex and possibly non-smooth loss function in deep learning problems.Our analysis establishes some first theoretical understanding into the observed robustness for batch normalization and weight normalization.

stat.ML↗

arXiv2020

Symplectic Recurrent Neural Networks

We propose Symplectic Recurrent Neural Networks (SRNNs) as learning algorithms that capture the dynamics of physical systems from observed trajectories. An SRNN models the Hamiltonian function of the system by a neural network and furthermore leverages symplectic integration, multiple-step training and initial state optimization to address the challenging numerical issues associated with Hamiltonian systems. We show that SRNNs succeed reliably on complex and noisy Hamiltonian systems. We also show how to augment the SRNN integration scheme in order to handle stiff dynamical systems such as bouncing billiards.

cs.LG↗

arXiv2020

Invariant Risk Minimization

We introduce Invariant Risk Minimization (IRM), a learning paradigm to estimate invariant correlations across multiple training distributions. To achieve this goal, IRM learns a data representation such that the optimal classifier, on top of that data representation, matches for all training distributions. Through theory and experiments, we show how the invariances learned by IRM relate to the causal structures governing the data and enable out-of-distribution generalization.

stat.ML↗

arXiv2019

On the Ineffectiveness of Variance Reduced Optimization for Deep Learning

The application of stochastic variance reduction to optimization has shown remarkable recent theoretical and practical success. The applicability of these techniques to the hard non-convex optimization problems encountered during training of modern deep neural networks is an open problem. We show that naive application of the SVRG technique and related approaches fail, and explore why.

cs.LG↗

arXiv2019

Cold Case: The Lost MNIST Digits

Although the popular MNIST dataset [LeCun et al., 1994] is derived from the NIST database [Grother and Hanaoka, 1995], the precise processing steps for this derivation have been lost to time. We propose a reconstruction that is accurate enough to serve as a replacement for the MNIST dataset, with insignificant changes in accuracy. We trace each MNIST digit to its NIST source and its rich metadata such as writer identifier, partition identifier, etc. We also reconstruct the complete MNIST test set with 60,000 samples instead of the usual 10,000. Since the balance 50,000 were never distributed, they enable us to investigate the impact of twenty-five years of MNIST experiments on the reported testing performances. Our results unambiguously confirm the trends observed by Recht et al. [2018, 2019]: although the misclassification rates are slightly off, classifier ordering and model selection remain broadly reliable. We attribute this phenomenon to the pairing benefits of comparing classifiers on the same digits.

cs.LG↗