Marco Romito

Andrea Agazzi, Giuseppe Bruno, Eloy Mosig García et al.

We prove pathwise convergence of the layerwise evolution of tokens in a finite-depth, finite-width transformer model with MultiLayer Perceptron (MLP) blocks to a continuous-time stochastic interacting particle system. We also identify the stochastic partial differential equation describing the evolution of the tokens' distribution in this limit and prove propagation of chaos when the number of such tokens is large. The bounds we establish are quantitative and the limits we consider commute. We further prove that the limiting stochastic model displays synchronization by noise and establish exponential dissipation of the interaction energy on average, provided that the common noise is sufficiently coercive relative to the deterministic self-attention drift. We finally characterize the activation functions satisfying the former condition.

Marco Romito, Francesco Triggiano

The signature is a fundamental object that describes paths (that is, continuous functions from an interval to a Euclidean space). Likewise, the expected signature provides a statistical description of the law of stochastic processes. We propose a feature extraction model for time series built upon the expected signature. This is computed through a Gaussian processes based data augmentation. One of the main features is that an optimal feature extraction is learnt through the supervised task that uses the model.

Filippo Giovagnini, Sotirios Kotitsas, Marco Romito

We consider the infinite-width limit of a fully connected deep neural network with general weights, and we prove quantitative general bounds on the $2$-Wasserstein distance between the network and its infinite-width Gaussian limit, under appropriate regularity assumptions on the activation function. Our main tool is a Lindeberg principle for Deep Neural Networks, which we use to successively replace the weights on each layer by Gaussian random variables.

Luca Callisti, Marco Romito, Francesco Triggiano

We present a theoretical analysis of some popular adaptive Stochastic Gradient Descent (SGD) methods in the small learning rate regime. Using the stochastic modified equations framework introduced by Li et al., we derive effective continuous stochastic dynamics for these methods. Our key contribution is that sampling-induced noise in SGD manifests in the limit as independent Brownian motions driving the parameter and gradient second momentum evolutions. Furthermore, extending the approach of Malladi et al., we investigate scaling rules between the learning rate and key hyperparameters in adaptive methods, characterising all non-trivial limiting dynamics.

Andrea Agazzi, Vittorio Carlei, Marco Romito et al.

Global optimization, particularly for non-convex functions with multiple local minima, poses significant challenges for traditional gradient-based methods. While metaheuristic approaches offer empirical effectiveness, they often lack theoretical convergence guarantees and may disregard available gradient information. This paper introduces a novel gradient-based swarm particle optimization method designed to efficiently escape local minima and locate global optima. Our approach leverages a "Soft-min Energy" interacting function, $J_β(\mathbf{x})$, which provides a smooth, differentiable approximation of the minimum function value within a particle swarm. We define a stochastic gradient flow in the particle space, incorporating a Brownian motion term for exploration and a time-dependent parameter $β$ to control smoothness, similar to temperature annealing. We theoretically demonstrate that for strongly convex functions, our dynamics converges to a stationary point where at least one particle reaches the global minimum, with other particles exhibiting exploratory behavior. Furthermore, we show that our method facilitates faster transitions between local minima by reducing effective potential barriers with respect to Simulated Annealing. More specifically, we estimate the hitting times of unexplored potential wells for our model in the small noise regime and show that they compare favorably with the ones of overdamped Langevin. Numerical experiments on benchmark functions, including double wells and the Ackley function, validate our theoretical findings and demonstrate better performance over the well-known Simulated Annealing method in terms of escaping local minima and achieving faster convergence.

Marco Miani, Maurizio Parton, Marco Romito

Having access to an exploring restart distribution (the so-called wide coverage assumption) is critical with policy gradient methods. This is due to the fact that, while the objective function is insensitive to updates in unlikely states, the agent may still need improvements in those states in order to reach a nearly optimal payoff. For this reason, wide coverage is used in some form when analyzing theoretical properties of practical policy gradient methods. However, this assumption can be unfeasible in certain environments, for instance when learning is online, or when restarts are possible only from a fixed initial state. In these cases, classical policy gradient algorithms can have very poor convergence properties and sample efficiency. In this paper, we develop Curious Explorer, a novel and simple iterative state space exploration strategy that can be used with any starting distribution $ρ$. Curious Explorer starts from $ρ$, then using intrinsic rewards assigned to the set of poorly visited states produces a sequence of policies, each one more exploratory than the previous one in an informed way, and finally outputs a restart model $μ$ based on the state visitation distribution of the exploratory policies. Curious Explorer is provable, in the sense that we provide theoretical upper bounds on how often an optimal policy visits poorly visited states. These bounds can be used to prove PAC convergence and sample efficiency results when a PAC optimizer is plugged in Curious Explorer. This allows to achieve global convergence and sample efficiency results without any coverage assumption for REINFORCE, and potentially for any other policy gradient method ensuring PAC convergence with wide coverage. Finally, we plug (the output of) Curious Explorer into REINFORCE and TRPO, and show empirically that it can improve performance in MDPs with challenging exploration.