66 citations · 71 across the 13 of their papers we have counts for
16 papers
Feature Selective Model Collapse in Diffusion Models: Total Replacement versus Fixed-Budget Training
Hanna Malet, Gabriel Turinici
Model collapse arises when generative models are trained on synthetic data produced by earlier models. The phenomenon has attracted considerable attention because of its societal a…
Spatial Strategies, Not Actions: Vector-Quantized Geodesics as Tools for LLM-Driven Agents
Gabriel Turinici
Large language model (LLM) based agents are often criticized for lacking spatial understanding and mainly exploiting statistical text patterns. We investigate their spatial compreh…
Inferring Missing Trajectory Data with Temporal Convolutional Networks
Ilinca Tiriblecea, Gabriel Turinici
Trajectory data collected in real-world settings is frequently incomplete due to sensor failure, communication loss, or occlusion. We address the task of \emph{trajectory inpaintin…
Physics-Informed Neural Networks for coupled stiff transport systems
Laetitia Laguzet, Gabriel Turinici
Physics-Informed Neural Networks (PINN) struggle with stiff, regime-changing transport equations due to instability, loss imbalance, and violations of physical consistency. This pa…
Model-Free Deep Hedging with Transaction Costs and Light Data Requirements
Pierre Brugière, Gabriel Turinici
Option pricing theory, such as the Black and Scholes (1973) model, provides an explicit solution to construct a strategy that perfectly hedges an option in a continuous-time settin…
Individual vaccination as Nash equilibrium in a SIR model with application to the 2009-10 Influenza A(H1N1) epidemic in France
Laetitia Laguzet, Gabriel Turinici
The vaccination against ongoing epidemics is seldom compulsory but remains one of the most classical means to fight epidemic propagation. However recent debates concerning the inno…
Transformer for Times Series: an Application to the S&P500
Pierre Brugiere, Gabriel Turinici
The transformer models have been extensively used with good results in a wide area of machine learning applications including Large Language Models and image generation. Here, we i…
Model free collision aggregation for the computation of escape distributions
Laetitia Laguzet, Gabriel Turinici
Motivated by a heat radiative transport equation, we consider a particle undergoing collisions in a space-time domain and propose a method to sample its escape time, space and dire…
Convergence of a L2 regularized Policy Gradient Algorithm for the Multi Armed Bandit
Stefana Anita, Gabriel Turinici
Although Multi Armed Bandit (MAB) on one hand and the policy gradient approach on the other hand are among the most used frameworks of Reinforcement Learning, the theoretical prope…
Onflow: a model free, online portfolio allocation algorithm robust to transaction fees
Gabriel Turinici, Pierre Brugiere
We introduce Onflow, a reinforcement learning method for optimizing portfolio allocation via gradient flows. Our approach dynamically adjusts portfolio allocations to maximize expe…
A cell-based population control of Monte Carlo particles for the global variance reduction for transport equations
Laetitia Laguzet, Gabriel Turinici
We present a population control method with sampling and regulation steps for Monte Carlo particles involved in the numerical simulation of a transport equation. We recall in the f…
The Quantization Monte Carlo method for solving radiative transport equations
Laetitia Laguzet, Gabriel Turinici
We introduce the Quantization Monte Carlo method to solve thermal radiative transport equations with possibly several collision regimes, ranging from few collisions to massive numb…
Deep Conditional Measure Quantization
Gabriel Turinici
Quantization of a probability measure means representing it with a finite set of Dirac masses that approximates the input distribution well enough (in some metric space of probabil…
Huber-energy measure quantization
Gabriel Turinici
We describe a measure quantization procedure i.e., an algorithm which finds the best approximation of a target probability law (and more generally signed finite variation measure)…
Algorithms that get old : the case of generative deep neural networks
Gabriel Turinici
Generative deep neural networks used in machine learning, like the Variational Auto-Encoders (VAE), and Generative Adversarial Networks (GANs) produce new objects each time when as…
Heterogeneous social interactions and the COVID-19 lockdown outcome in a multi-group SEIR model
Jean Dolbeault, Gabriel Turinici
We study variants of the SEIR model for interpreting some qualitative features of the statistics of the Covid-19 epidemic in France. Standard SEIR models distinguish essentially tw…