10 citations · 35 across the 19 of their papers we have counts for
22 papers
Jumping up and down: Denoiser diffusion models for discrete ordinal data
Yair Shenfeld, Ricardo Baptista, Stefano Peluchetti
Diffusion models are highly developed in continuous spaces for image and video domains. Recently, major advances have been made for discrete diffusion models for categorical data,…
Bridging Spherical Black-Box Optimizers
Johannes Ackermann, Stefano Peluchetti
When gradient information is unavailable, black-box optimization (BBO) methods provide a practical alternative. While Evolution Strategies (ES), Consensus-Based Optimization (CBO),…
KamonBench: A Grammar-Based Dataset for Evaluating Compositional Factor Recovery in Vision-Language Models
Richard Sproat, Stefano Peluchetti
Kamon (family crests) are an important part of Japanese culture and a natural test case for compositional visual recognition: each crest combines a small number of symbolic choices…
Binomial flows: Denoising and flow matching for discrete ordinal data
Yair Shenfeld, Ricardo Baptista, Stefano Peluchetti
Flow-based generative modeling in continuous spaces exploit Tweedie's formula to express the denoiser (learned in training) as a score function (used in sampling). In contrast, thi…
Sparser, Faster, Lighter Transformer Language Models
Edoardo Cetin, Stefano Peluchetti, Emilio Castillo +3
Scaling autoregressive large language models (LLMs) has driven unprecedented progress but comes with vast computational costs. In this work, we tackle these costs by leveraging uns…
Latent-Augmented Discrete Diffusion Models
Dario Shariatian, Alain Durmus, Umut Simsekli +1
Discrete diffusion models have emerged as a powerful class of models and a promising route to fast language generation, but practical implementations typically rely on factored rev…
BM: Coupled Schrödinger Bridge Matching
Stefano Peluchetti
A Schrödinger bridge establishes a dynamic transport map between two target distributions via a reference process, simultaneously solving an associated entropic optimal transport p…
Function-Space MCMC for Bayesian Wide Neural Networks
Lucia Pezzetti, Stefano Favaro, Stefano Peluchetti
Bayesian Neural Networks represent a fascinating confluence of deep learning and probabilistic reasoning, offering a compelling framework for understanding uncertainty in complex p…
Non-Denoising Forward-Time Diffusions
Stefano Peluchetti
The scope of this paper is generative modeling through diffusion processes. An approach falling within this paradigm is the work of Song et al. (2021), which relies on a time-rever…
Diffusion Bridge Mixture Transports, Schrödinger Bridge Problems and Generative Modeling
Stefano Peluchetti
The dynamic Schrödinger bridge problem seeks a stochastic process that defines a transport between two target probability measures, while optimally satisfying the criteria of being…
Large-width asymptotics for ReLU neural networks with -Stable initializations
Stefano Favaro, Sandra Fortini, Stefano Peluchetti
There is a recent and growing literature on large-width asymptotic properties of Gaussian neural networks (NNs), namely NNs whose weights are initialized as Gaussian distributions.…
Deep Stable neural networks: large-width asymptotics and convergence rates
Stefano Favaro, Sandra Fortini, Stefano Peluchetti
In modern deep learning, there is a recent and growing literature on the interplay between large-width asymptotic properties of deep Gaussian neural networks (NNs), i.e. deep NNs w…
Learning Stochastic Optimal Policies via Gradient Descent
Stefano Massaroli, Michael Poli, Stefano Peluchetti +3
We systematically develop a learning-based treatment of stochastic optimal control (SOC), relying on direct optimization of parametric control policies. We propose a derivation of…
Large-width functional asymptotics for deep Gaussian neural networks
Daniele Bracale, Stefano Favaro, Sandra Fortini +1
In this paper, we consider fully connected feed-forward deep neural networks where weights and biases are independent and identically distributed according to Gaussian distribution…
A Bayesian nonparametric approach to count-min sketch under power-law data streams
Emanuele Dolera, Stefano Favaro, Stefano Peluchetti
The count-min sketch (CMS) is a randomized data structure that provides estimates of tokens' frequencies in a large data stream using a compressed representation of the data by ran…
Learning-augmented count-min sketches via Bayesian nonparametrics
Emanuele Dolera, Stefano Favaro, Stefano Peluchetti
The count-min sketch (CMS) is a time and memory efficient randomized data structure that provides estimates of tokens' frequencies in a data stream of tokens, i.e. point queries, b…
Infinite-channel deep stable convolutional neural networks
Daniele Bracale, Stefano Favaro, Sandra Fortini +1
The interplay between infinite-width neural networks (NNs) and classes of Gaussian processes (GPs) is well known since the seminal work of Neal (1996). While numerous theoretical r…
Doubly infinite residual neural networks: a diffusion process approach
Stefano Peluchetti, Stefano Favaro
Modern neural networks (NN) featuring a large number of layers (depth) and units per layer (width) have achieved a remarkable performance across many domains. While there exists a…
Stable behaviour of infinitely wide deep neural networks
Stefano Favaro, Sandra Fortini, Stefano Peluchetti
We consider fully connected feed-forward deep neural networks (NNs) where weights and biases are independent and identically distributed as symmetric centered stable distributions.…
An empirical study of pretrained representations for few-shot classification
Tiago Ramalho, Thierry Sousbie, Stefano Peluchetti
Recent algorithms with state-of-the-art few-shot classification results start their procedure by computing data features output by a large pretrained model. In this paper we system…
Infinitely deep neural networks as diffusion processes
Stefano Peluchetti, Stefano Favaro
When the parameters are independently and identically distributed (initialized) neural networks exhibit undesirable properties that emerge as the number of layers increases, e.g. a…
ε-Strong simulation of the Brownian path
Alexandros Beskos, Stefano Peluchetti, Gareth Roberts
We present an iterative sampling method which delivers upper and lower bounding processes for the Brownian path. We develop such processes with particular emphasis on being able to…