Emanuele Troiani

25 papers A* 3A 2Journal 19Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	A solvable high-dimensional model where nonlinear autoencoders learn structure invisible to PCA while test loss misaligns with generalization. CoRR Vicente Conde Mendes, Lorenzo Bardone, Cédric Koller, Jorge Medina Moreira, Vittorio Erba, Emanuele Troiani, Lenka Zdeborová
2025	J	`jnl`	Bayes optimal learning of attention-indexed models. CoRR Fabrizio Boncoraglio, Emanuele Troiani, Vittorio Erba, Lenka Zdeborová
2025	A	`conf`	Fundamental computational limits of weak learnability in high-dimensional multi-index models. AISTATS Emanuele Troiani, Yatin Dandi, Leonardo Defilippis, Lenka Zdeborová, Bruno Loureiro, Florent Krzakala
2025	J	`jnl`	Fundamental limits of learning in sequence multi-index models and deep attention networks: High-dimensional asymptotics and sharp thresholds. CoRR Emanuele Troiani, Hugo Cui, Yatin Dandi, Florent Krzakala, Lenka Zdeborová
2025	A*	`conf`	Fundamental limits of learning in sequence multi-index models and deep attention networks: high-dimensional asymptotics and sharp thresholds. ICML Emanuele Troiani, Hugo Cui, Yatin Dandi, Florent Krzakala, Lenka Zdeborová
2025	J	`jnl`	Inductive Bias and Spectral Properties of Single-Head Attention in High Dimensions. CoRR Fabrizio Boncoraglio, Vittorio Erba, Emanuele Troiani, Florent Krzakala, Lenka Zdeborová
2025	J	`jnl`	Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime. CoRR Leonardo Defilippis, Yizhou Xu, Julius Girardin, Emanuele Troiani, Vittorio Erba, Lenka Zdeborová, Bruno Loureiro, Florent Krzakala
2025	J	`jnl`	The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks. CoRR Vittorio Erba, Emanuele Troiani, Lenka Zdeborová, Florent Krzakala
2024	A	`conf`	Asymptotic Characterisation of the Performance of Robust Linear Regression in the Presence of Outliers. AISTATS Matteo Vilucchio, Emanuele Troiani, Vittorio Erba, Florent Krzakala
2024	A*	`conf`	Bayes-optimal learning of an extensive-width neural network from quadratically many samples. NeurIPS Antoine Maillard, Emanuele Troiani, Simon Martin, Florent Krzakala, Lenka Zdeborová
2024	J	`jnl`	Bayes-optimal learning of an extensive-width neural network from quadratically many samples. CoRR Antoine Maillard, Emanuele Troiani, Simon Martin, Florent Krzakala, Lenka Zdeborová
2024	J	`jnl`	Bilinear Sequence Regression: A Model for Learning from Long Sequences of High-dimensional Tokens. CoRR Vittorio Erba, Emanuele Troiani, Luca Biggio, Antoine Maillard, Lenka Zdeborová
2024	J	`jnl`	Could ChatGPT get an Engineering Degree? Evaluating Higher Education Vulnerability to AI Assistants. CoRR Beatriz Borges, Negar Foroutan, Deniz Bayazit, Anna Sotnikova, Syrielle Montariol, Tanya Nazaretzky, Mohammadreza Banaei, Alireza Sakhaeirad, Philippe Servant, Seyed Parsa Neshaei, Jibril Frej, Angelika Romanou, Gail Weiss, Sepideh Mamooler, Zeming Chen, Simin Fan, Silin Gao, Mete Ismayilzada, Debjit Paul, Alexandre Schöpfer, Andrej Janchevski, Anja Tiede, Clarence Linden, Emanuele Troiani, Francesco Salvi, Freya Behrens, Giacomo Orsi, Giovanni Piccioli, Hadrien Sevel, Louis Coulon, Manuela Pineros-Rodriguez, Marin Bonnassies, Pierre Hellich, Puck van Gerwen, Sankalp Gambhir, Solal Pirelli, Thomas Blanchard, Timothée Callens, Toni Abi Aoun, Yannick Calvino Alonso, Yuri Cho, Alberto Silvio Chiappa, Antonio Sclocchi, Étienne Bruno, Florian Hofhammer, Gabriel Pescia, Geovani Rizk, Leello Dadi, Lucas Stoffl, Manoel Horta Ribeiro, Matthieu Bovel, Yueyang Pan, Aleksandra Radenovic, Alexandre Alahi, Alexander Mathis, Anne-Florence Bitbol, Boi Faltings, Cécile Hébert, Devis Tuia, François Maréchal, George Candea, Giuseppe Carleo, Jean-Cédric Chappelier, Nicolas Flammarion, Jean-Marie Fürbringer, Jean-Philippe Pellet, Karl Aberer, Lenka Zdeborová, Marcel Salathé, Martin Jaggi, Martin Rajman, Mathias Payer, Matthieu Wyart, Michael Gastpar, Michele Ceriotti, Ola Svensson, Olivier Lévêque, Paolo Ienne, Rachid Guerraoui, Robert West, Sanidhya Kashyap, Valerio Piazza, Viesturs Simanis, Viktor Kuncak, Volkan Cevher, Philippe Schwaller, Sacha Friedli, Patrick Jermann, Tanja Käser, Antoine Bosselut
2024	J	`jnl`	Fundamental limits of weak learnability in high-dimensional multi-index models. CoRR Emanuele Troiani, Yatin Dandi, Leonardo Defilippis, Lenka Zdeborová, Bruno Loureiro, Florent Krzakala
2024	J	`jnl`	Rigorous Dynamical Mean-Field Theory for Stochastic Gradient Descent Methods. SIAM J. Math. Data Sci. Cédric Gerbelot, Emanuele Troiani, Francesca Mignacco, Florent Krzakala, Lenka Zdeborová
2024	A*	`conf`	The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents. ICML Yatin Dandi, Emanuele Troiani, Luca Arnaboldi, Luca Pesce, Lenka Zdeborová, Florent Krzakala
2024	J	`jnl`	The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents. CoRR Yatin Dandi, Emanuele Troiani, Luca Arnaboldi, Luca Pesce, Lenka Zdeborová, Florent Krzakala
2023	J	`jnl`	Asymptotic Characterisation of Robust Empirical Risk Minimisation Performance in the Presence of Outliers. CoRR Matteo Vilucchio, Emanuele Troiani, Vittorio Erba, Florent Krzakala
2023	J	`jnl`	Gibbs Sampling the Posterior of Neural Networks. CoRR Giovanni Piccioli, Emanuele Troiani, Lenka Zdeborová
2023	J	`jnl`	Sparse Representations, Inference and Learning. CoRR Clarissa Lauditi, Emanuele Troiani, Marc Mézard
2022	—	`conf`	Optimal denoising of rotationally invariant rectangular matrices. MSML Emanuele Troiani, Vittorio Erba, Florent Krzakala, Antoine Maillard, Lenka Zdeborová
2022	J	`jnl`	Optimal denoising of rotationally invariant rectangular matrices. CoRR Emanuele Troiani, Vittorio Erba, Florent Krzakala, Antoine Maillard, Lenka Zdeborová
2022	J	`jnl`	Rigorous dynamical mean field theory for stochastic gradient descent methods. CoRR Cédric Gerbelot, Emanuele Troiani, Francesca Mignacco, Florent Krzakala, Lenka Zdeborová
2020	J	`jnl`	Stuttering Conway Sequences Are Still Conway Sequences. CoRR Éric Brier, Rémi Géraud-Stewart, David Naccache, Alessandro Pacco, Emanuele Troiani
2020	J	`jnl`	The Look-and-Say The Biggest Sequence Eventually Cycles. CoRR Éric Brier, Rémi Géraud-Stewart, David Naccache, Alessandro Pacco, Emanuele Troiani