Pierre Marion - RankMe

31 papers A* 7A 1Journal 21Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Clustering in Deep Stochastic Transformers. CoRR Lev Fedorov, Michael E. Sander, Romuald Elie, Pierre Marion, Mathieu Laurière
2026	J	`jnl`	Exponential Convergence of (Stochastic) Gradient Descent for Separable Logistic Regression. CoRR Sacchit Kale, Piyushi Manupriya, Pierre Marion, Francis R. Bach, Anant Raj
2025	A*	`conf`	Attention layers provably solve single-location regression. ICLR Pierre Marion, Raphaël Berthier, Gérard Biau, Claire Boyer
2025	J	`jnl`	Attention-based clustering. CoRR Rodrigo Maulen-Soto, Claire Boyer, Pierre Marion
2025	A	`conf`	Implicit Diffusion: Efficient optimization through stochastic sampling. AISTATS Pierre Marion, Anna Korba, Peter L. Bartlett, Mathieu Blondel, Valentin De Bortoli, Arnaud Doucet, Felipe Llinares-López, Courtney Paquette, Quentin Berthet
2025	J	`jnl`	Large Stepsizes Accelerate Gradient Descent for Regularized Logistic Regression. CoRR Jingfeng Wu, Pierre Marion, Peter L. Bartlett
2025	J	`jnl`	Optimal Stopping in Latent Diffusion Models. CoRR Yu-Han Wu, Quentin Berthet, Gérard Biau, Claire Boyer, Romuald Elie, Pierre Marion
2025	J	`jnl`	Phase Diagram of Dropout for Two-Layer Neural Networks in the Mean-Field Regime. CoRR Lénaïc Chizat, Pierre Marion, Yerkin Yesbay
2025	J	`jnl`	Scaling ResNets in the Large-depth Regime. J. Mach. Learn. Res. Pierre Marion, Adeline Fermanian, Gérard Biau, Jean-Philippe Vert
2025	J	`jnl`	Statistical Advantage of Softmax Attention: Insights from Single-Location Regression. CoRR O. Duranthon, Pierre Marion, Claire Boyer, Bruno Loureiro, Lenka Zdeborová
2025	A*	`conf`	Taking a Big Step: Large Learning Rates in Denoising Score Matching Prevent Memorization. COLT Yu-Han Wu, Pierre Marion, Gérard Biau, Claire Boyer
2025	J	`jnl`	Taking a Big Step: Large Learning Rates in Denoising Score Matching Prevent Memorization. CoRR Yu-Han Wu, Pierre Marion, Gérard Biau, Claire Boyer
2024	J	`jnl`	Attention layers provably solve single-location regression. CoRR Pierre Marion, Raphaël Berthier, Gérard Biau, Claire Boyer
2024	A*	`conf`	Deep linear networks for regression are implicitly regularized towards flat minima. NeurIPS Pierre Marion, Lénaïc Chizat
2024	J	`jnl`	Deep linear networks for regression are implicitly regularized towards flat minima. CoRR Pierre Marion, Lénaïc Chizat
2024	J	`jnl`	Implicit Diffusion: Efficient Optimization through Stochastic Sampling. CoRR Pierre Marion, Anna Korba, Peter L. Bartlett, Mathieu Blondel, Valentin De Bortoli, Arnaud Doucet, Felipe Llinares-López, Courtney Paquette, Quentin Berthet
2024	A*	`conf`	Implicit regularization of deep residual networks towards neural ODEs. ICLR Pierre Marion, Yu-Han Wu, Michael Eli Sander, Gérard Biau
2023	A*	`conf`	Generalization bounds for neural ordinary differential equations and deep residual networks. NeurIPS Pierre Marion
2023	J	`jnl`	Generalization bounds for neural ordinary differential equations and deep residual networks. CoRR Pierre Marion
2023	J	`jnl`	Implicit regularization of deep residual networks towards neural ODEs. CoRR Pierre Marion, Yu-Han Wu, Michael E. Sander, Gérard Biau
2023	J	`jnl`	Leveraging the two timescale regime to demonstrate convergence of neural networks. CoRR Pierre Marion, Raphaël Berthier
2023	A*	`conf`	Leveraging the two-timescale regime to demonstrate convergence of neural networks. NeurIPS Pierre Marion, Raphaël Berthier
2022	J	`jnl`	Scaling ResNets in the Large-depth Regime. CoRR Pierre Marion, Adeline Fermanian, Gérard Biau, Jean-Philippe Vert
2021	A*	`conf`	Framing RNN as a kernel method: A neural ODE approach. NeurIPS Adeline Fermanian, Pierre Marion, Jean-Philippe Vert, Gérard Biau
2021	J	`jnl`	Framing RNN as a kernel method: A neural ODE approach. CoRR Adeline Fermanian, Pierre Marion, Jean-Philippe Vert, Gérard Biau
2021	—	`conf`	Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs. EMNLP (1) Pierre Marion, Pawel Krzysztof Nowak, Francesco Piccinno
2021	J	`jnl`	Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs. CoRR Pierre Marion, Pawel Krzysztof Nowak, Francesco Piccinno
2020	—	`conf`	A Tool for Custom Construction of QMC and RQMC Point Sets. MCQMC Pierre L'Ecuyer, Pierre Marion, Maxime Godin, Florian Puchhammer
2020	J	`jnl`	A Tool for Custom Construction of QMC and RQMC Point Sets. CoRR Pierre L'Ecuyer, Pierre Marion, Maxime Godin, Florian Puchhammer
2020	J	`jnl`	An algorithm to compute the t-value of a digital net and of its projections. J. Comput. Appl. Math. Pierre Marion, Maxime Godin, Pierre L'Ecuyer
2019	J	`jnl`	An algorithm to compute the t-value of a digital net and of its projections. CoRR Pierre Marion, Maxime Godin, Pierre L'Ecuyer