Are you an EPFL student looking for a semester project?

Work with us on data science and visualisation projects, and deploy your project as an app on top of GraphSearch.

Graph
Search

fr|en

Person

Nicolas Henri Bernard Flammarion

Related publications (32)

Model agnostic methods meta-learn despite misspecifications

Nicolas Henri Bernard Flammarion, Oguz Kaan Yüksel

Due to its empirical success on few shot classification and reinforcement learning, meta-learning recently received a lot of interest. Meta-learning leverages data from previous tasks to quickly learn a new task, despite limited data. In particular, model agnostic methods look for initialisation points from which gradient descent quickly adapts to any new task. Although it has been empirically suggested that such methods learn a good shared representation during training, there is no strong theoretical evidence of such behavior. More importantly, it is unclear whether these methods truly are model agnostic, i.e., whether they still learn a shared structure despite architecture misspecifications. To fill this gap, this work shows in the limit of an infinite number of tasks that first order ANIL with a linear two-layer network architecture successfully learns a linear shared representation. Moreover, this result holds despite misspecifications: having a large width with respect to the hidden dimension of the shared representation does not harm the algorithm performance. The learnt parameters then allow to get a small test loss after a single gradient step on any new task. Overall this illustrates how well model agnostic methods can adapt to any (unknown) model structure.

2023

Penalising the biases in norm regularisation enforces sparsity

Nicolas Henri Bernard Flammarion

Controlling the parameters' norm often yields good generalisation when training neural networks. Beyond simple intuitions, the relation between parameters' norm and obtained estimators theoretically remains misunderstood. For one hidden ReLU layer networks with unidimensional data, this work shows the minimal parameters' norm required to represent a function is given by the total variation of its second derivative, weighted by a

\sqrt{1+x^2}

factor. As a comparison, this

\sqrt{1+x^2}

weighting disappears when the norm of the bias terms are ignored. This additional weighting is of crucial importance, since it is shown in this work to enforce uniqueness and sparsity (in number of kinks) of the minimal norm interpolator. On the other hand, omitting the bias' norm allows for non-sparse solutions. Penalising the bias terms in the regularisation, either explicitly or implicitly, thus leads to sparse estimators. This sparsity might take part in the good generalisation of neural networks that is empirically observed.

2023

Accelerated SGD for Non-Strongly-Convex Least Squares

Nicolas Henri Bernard Flammarion, Aditya Vardhan Varre

We consider stochastic approximation for the least squares regression problem in the non-strongly convex setting. We present the first practical algorithm that achieves the optimal prediction error rates in terms of dependence on the noise of the problem, as

O(d/t)

while accelerating the forgetting of the initial conditions to

O(d/t^2)

. Our new algorithm is based on a simple modification of the accelerated gradient descent. We provide convergence results for both the averaged and the last iterate of the algorithm. In order to describe the tightness of these new bounds, we present a matching lower bound in the noiseless setting and thus show the optimality of our algorithm.

2022

An Efficient Sampling Algorithm for Non-smooth Composite Potentials

Nicolas Henri Bernard Flammarion

We consider the problem of sampling from a density of the form p(x) ? exp(-f (x) - g(x)), where f : Rd-+ R is a smooth function and g : R-d-+ R is a convex and Lipschitz function. We propose a new algorithm based on the Metropolis-Hastings framework. Under certain isoperimetric inequalities on the target density, we prove that the algorithm mixes to within total variation (TV) distance e of the target density in at most O(d log(d/e)) iterations. This guarantee extends previous results on sampling from distributions with smooth log densities (g = 0) to the more general composite non-smooth case, with the same mixing time up to a multiple of the condition number. Our method is based on a novel proximal-based proposal distribution that can be efficiently computed for a large class of non-smooth functions g. Simulation results on posterior sampling problems that arise from the Bayesian Lasso show empirical advantage over previous proposal distributions.

MICROTOME PUBL2022

Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs

Nicolas Henri Bernard Flammarion, Loucas Pillaud-Vivien

The training of neural networks by gradient descent methods is a cornerstone of the deep learning revolution. Yet, despite some recent progress, a complete theory explaining its success is still missing. This article presents, for orthogonal input vectors, a precise description of the gradient flow dynamics of training one-hidden layer ReLU neural networks for the mean squared error at small initialisation. In this setting, despite non-convexity, we show that the gradient flow converges to zero loss and characterise its implicit bias towards minimum variation norm. Furthermore, some interesting phenomena are highlighted: a quantitative description of the initial alignment phenomenon and a proof that the process follows a specific saddle to saddle dynamics.

2022

Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks

Maksym Andriushchenko, Nicolas Henri Bernard Flammarion

We propose a versatile framework based on random search, Sparse-RS, for score-based sparse targeted and untargeted attacks in the black-box setting. Sparse-RS does not rely on substitute models and achieves state-of-the-art success rate and query efficiency for multiple sparse attack models: l(0)-bounded perturbations, adversarial patches, and adversarial frames. The l(0)-version of untargeted Sparse-RS outperforms all black-box and even all white-box attacks for different models on MNIST, CIFAR-10, and ImageNet. Moreover, our untargeted Sparse-RS achieves very high success rates even for the challenging settings of 20 x 20 adversarial patches and 2-pixel wide adversarial frames for 224 x 224 images. Finally, we show that Sparse-RS can be applied to generate targeted universal adversarial patches where it significantly outperforms the existing approaches. Our code is available at https://github.com/fra31/sparse-rs.

ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE2022

Towards Understanding Sharpness-Aware Minimization

Maksym Andriushchenko, Nicolas Henri Bernard Flammarion

Sharpness-Aware Minimization (SAM) is a recent training method that relies on worst-case weight perturbations which significantly improves generalization in various settings. We argue that the existing justifications for the success of SAM which are based on a PAC-Bayes generalization bound and the idea of convergence to flat minima are incomplete. Moreover, there are no explanations for the success of using m-sharpness in SAM which has been shown as essential for generalization. To better understand this aspect of SAM, we theoretically analyze its implicit bias for diagonal linear networks. We prove that SAM always chooses a solution that enjoys better generalization properties than standard gradient descent for a certain class of problems, and this effect is amplified by using m-sharpness. We further study the properties of the implicit bias on non-linear networks empirically, where we show that fine-tuning a standard model with SAM can lead to significant generalization improvements. Finally, we provide convergence results of SAM for non-convex objectives when used with stochastic gradients. We illustrate these results empirically for deep networks and discuss their relation to the generalization behavior of SAM.

JMLR-JOURNAL MACHINE LEARNING RESEARCH2022

Trace norm regularization for multi-task learning with scarce data

Nicolas Henri Bernard Flammarion, Mikhail Konobeev

Multi-task learning leverages structural similarities between multiple tasks to learn despite very few samples. Motivated by the recent success of neural networks applied to data-scarce tasks, we consider a linear low-dimensional shared representation model. Despite an extensive literature, existing theoretical results either guarantee weak estimation rates or require a large number of samples per task. This work provides the first estimation error bound for the trace norm regularized estimator when the number of samples per task is small. The advantages of trace norm regularization for learning data-scarce tasks extend to meta-learning and are confirmed empirically on synthetic datasets.

2022

A Continuized View on Nesterov Acceleration

Nicolas Henri Bernard Flammarion

We introduce the "continuized" Nesterov acceleration, a close variant of Nesterov acceleration whose variables are indexed by a continuous time parameter. The two variables continuously mix following a linear ordinary differential equation and take gradient steps at random times. This continuized variant benefits from the best of the continuous and the discrete frameworks: as a continuous process, one can use differential calculus to analyze convergence and obtain analytical expressions for the parameters; but a discretization of the continuized process can be computed exactly with convergence rates similar to those of Nesterov original acceleration. We show that the discretization has the same structure as Nesterov acceleration, but with random parameters.

2021

, ,

Understanding the implicit bias of training algorithms is of crucial importance in order to explain the success of overparametrised neural networks. In this paper, we study the dynamics of stochastic gradient descent over diagonal linear networks through its continuous time version, namely stochastic gradient flow. We explicitly characterise the solution chosen by the stochastic flow and prove that it always enjoys better generalisation properties than that of gradient flow. Quite surprisingly, we show that the convergence speed of the training loss controls the magnitude of the biasing effect: the slower the convergence, the better the bias. To fully complete our analysis, we provide convergence guarantees for the dynamics. We also give experimental results which support our theoretical claims. Our findings highlight the fact that structured noise can induce better generalisation and they help explain the greater performances observed in practice of stochastic gradient descent over gradient descent.

2021

Penalising the biases in norm regularisation enforces sparsity

Nicolas Henri Bernard Flammarion

\sqrt{1+x^2}

factor. As a comparison, this

\sqrt{1+x^2}

2023

Accelerated SGD for Non-Strongly-Convex Least Squares

Nicolas Henri Bernard Flammarion, Aditya Vardhan Varre

O(d/t)

while accelerating the forgetting of the initial conditions to

O(d/t^2)

2022