07:00
08:00
09:00
10:00
11:00
12:00
13:00
14:00
15:00
16:00
17:00
18:00
19:00
20:00
7:30 - 8:30 (1h)
Breakfast
9:15 - 9:45 (30min)
Welcome speech
9:45 - 10:45 (1h)
The Marauders Map of adversarial examples: State of knowledge on evasion attacks in machine learning (1/3)
Conference room
Rafael Pinot
10:45 - 11:15 (30min)
Coffee break
11:15 - 12:15 (1h)
Convex Optimization and First-Order Algorithms for Data Science (1/3)
Conference room
Adrien Taylor
12:30 - 13:30 (1h)
Lunch
13:30 - 15:55 (2h25)
Free time
15:55 - 16:45 (50min)
Approximating Optimal Transport plans with Sliced-Wasserstein
Conference room
Laetitia Chapel
16:45 - 17:15 (30min)
Coffee break
17:15 - 17:45 (30min)
Speed presentation from participants
Conference room
17:45 - 19:00 (1h15)
CT - Session 1
Conference room
› Continuous sparse estimation of a Gaussian Mixture Model with unknown covariances
- Romane Giard, Institut Camille Jordan
17:45-18:10 (25min)
› UNHaP : Unmixing Noise from Hawkes Processes
- Virginie Loison, Modèles et inférence pour les données de Neuroimagerie, Marqueurs cardiovasculaires en situation de stress
18:10-18:35 (25min)
› Optimal transport with Heterogenously Missing Data
- Linus Bleistein, Inria de Paris, Artificial Intelligence Laboratory [EPFL], Université Paris Dauphine-PSL
18:35-19:00 (25min)
19:30 - 20:30 (1h)
Dinner
7:30 - 8:30 (1h)
Breakfast
8:45 - 9:45 (1h)
The Marauders Map of adversarial examples: State of knowledge on evasion attacks in machine learning (2/3)
Conference room
Rafael Pinot
9:45 - 10:45 (1h)
Convex Optimization and First-Order Algorithms for Data Science (2/3)
Adrien Taylor
10:45 - 11:15 (30min)
Coffee break
11:15 - 12:15 (1h)
Transport based generative modeling and applications to sampling (1/3)
Conference room
Marylou Gabrié
12:30 - 13:30 (1h)
Lunch
13:30 - 15:30 (2h)
Free time
15:30 - 16:45 (1h15)
CT - Session 2
Conference room
› When to Forget? Complexity Trade-offs in Machine Unlearning
- Martin Van Waerebeke, Centre Inria de Paris
15:30-15:55 (25min)
› Consensus Monte Carlo for mixtures of categorical distributions
- Julie Fendler, MRC Biostatistics Unit, University of Cambridge
15:55-16:20 (25min)
› Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean-Field Games
- Antonio Ocello, ENSAE
16:20-16:45 (25min)
16:45 - 17:15 (30min)
Coffee break
17:15 - 18:05 (50min)
Optimization bilevel et unrolling
Conference room
Thomas Moreau
18:10 - 19:00 (50min)
Machine learning and numerical simulations. Interplay between data and physical models.
Conference room
Mathilde Mougeot
19:30 - 20:30 (1h)
Dinner
7:30 - 8:30 (1h)
Breakfast
8:45 - 9:45 (1h)
The Marauders Map of adversarial examples: State of knowledge on evasion attacks in machine learning (3/3)
Conference room
Rafael Pinot
9:45 - 10:45 (1h)
Convex Optimization and First-Order Algorithms for Data Science (3/3)
Conference room
Adrien Taylor
10:45 - 11:15 (30min)
Coffee break
11:15 - 12:15 (1h)
Conformal prediction - from a general introduction towards conditional guarantees (1/3)
Conference room
Aymeric Dieuleveut
12:30 - 13:30 (1h)
Lunch
13:30 - 15:30 (2h)
Free time
15:30 - 16:45 (1h15)
CT - Session 3
› Approche bayésienne pour évaluer l'incertitude et la robustesse d'indicateurs de graphes en neurosciences
- Alice Chevaux, INRIA
15:30-15:55 (25min)
› Iterated forward scheme to construct proposals for sequential Monte Carlo algorithms
- Sylvain Procope-Mamert, Mathématiques et Informatique Appliquées du Génome à l'Environnement [Jouy-En-Josas]
15:55-16:20 (25min)
› PAC-Bayesian Reconstruction Guarantees for Variational Autoencoders for Time Series
- Chloé Hashimoto-Cullen, Laboratoire de Probabilités, Statistique et Modélisation
16:20-16:45 (25min)
17:00 - 19:15 (2h15)
Poster session
› Benign landscape for Burer-Monteiro factorizations of MaxCut-type semidefinite programs
- Faniriana Rakoto Endor, CEntre de REcherches en MAthématiques de la DEcision
17:00-19:15 (2h15)
› Validation of Computer Codes via Mixture Model Estimation
- Negar Soleimani, AgroParisTech
17:00-19:15 (2h15)
› Variational Inference with Mixture of Isotropic Gaussians
- Marguerite Petit Talamon, Centre de Recherche en Économie et Statistique
17:00-19:15 (2h15)
› Statistical and Geometrical properties of regularized Kernel Kullback-Leibler divergence
- Clémentine Chazal, Centre de Recherche en Économie et Statistique
17:00-19:15 (2h15)
› Gradient-free variational inference within exponential families using least squares regression with applications on discrete distributions and likelihood-free models
- Le Fay Yvan, Centre de Recherche en Économie et Statistique
17:00-19:15 (2h15)
› Understanding the bias induced by Local Differential Privacy
- Jean Dufraiche, MAGNET (Machine Learning in Information Networks)
17:00-19:15 (2h15)
› TAMIS: Tailored Membership Inference Attacks on Synthetic Data
- Paul Andrey, MAGNET (Machine Learning in Information Networks)
17:00-19:15 (2h15)
› Growing Neural Networks: Spotting Expressivity Bottlenecks and Fixing Them Optimally
- Théo Rudkiewicz, TAU team
17:00-19:15 (2h15)
› Joint estimation of bipartite network collections. Application to plant-pollinator networks
- Louis LACOSTE, Mathématiques et Informatique Appliquées
17:00-19:15 (2h15)
› Harnessing Mixed Features for Imbalance Data Oversampling: Application to Bank Customers Scoring
- Abdoulaye SAKHO, Laboratoire de Probabilités, Statistique et Modélisation, Artefact [Paris]
17:00-19:15 (2h15)
› Hallucinations in statistical inverse problems: discussion, characterization and exploration in PET imaging
- Ramy Merabet, Centre Borelli
17:00-19:15 (2h15)
› Streaming Federated Learning with Markovian Data
- Tan-Khiem HUYNH, Centre Inria de Lyon
17:00-19:15 (2h15)
› Mask-Conditional Coverage for General Missing Data Mechanisms
- Jiarong FAN, Université Paris Saclay
17:00-19:15 (2h15)
› Weakly supervised learning methods for the classification of patients from flow cytometry data
- Pierre-André Mikem, Laboratoire de Mathématiques d'Orsay, Metafora biosystems
17:00-19:15 (2h15)
› Group-Specific Thresholding to Preserve Fairness of Stochastic Classifiers
- Shreya Venugopal, Machine Learning in Information Networks
17:00-19:15 (2h15)
› Better Capturing Interactions between Products in Retail: Revisited Negative Sampling for Basket Choice Modeling
- Vincent Auriau, Mathématiques et Informatique pour la Complexité et les Systèmes, Artefact Research Center
17:00-19:15 (2h15)
› Time Series Motif Discovery: A Comprehensive Evaluation
- Valerio Guerrini, CB - Centre Borelli - UMR 9010
17:00-19:15 (2h15)
› Set To Be Fair: Set-Valued Classification Under Fairness Constraints
- Eyal Cohen, Laboratoire de Probabilités, Statistique et Modélisation, Mathématiques Appliquées Paris 5, Statistique, Analyse et Modélisation Multidisciplinaire (SAmos-Marin Mersenne)
17:00-19:15 (2h15)
19:30 - 20:30 (1h)
Dinner
7:30 - 8:30 (1h)
Breakfast
8:45 - 9:45 (1h)
Conformal prediction - from a general introduction towards conditional guarantees (2/3)
Conference room
Aymeric Dieuleveut
9:45 - 10:45 (1h)
Transport based generative modeling and applications to sampling (2/3)
Conference room
Marylou Gabrié
10:45 - 11:15 (30min)
Coffee break
11:15 - 12:15 (1h)
CT - Session 4
Conference room
› Estimating ratios of normalizing constants using stochastic approximation: the SARIS algorithm
- Charlotte Baey, Université de Lille
11:15-11:45 (30min)
› Bayesian deep learning, overview and challenges
- Julyan Arbel, INRIA
11:45-12:15 (30min)
12:30 - 13:30 (1h)
Lunch
13:30 - 15:30 (2h)
Free time
15:30 - 16:45 (1h15)
CT - Session 5
Conference room
› Equivariant U-Nets for effective image deblurring: design principles and challenges
- Jérémy Scanvic, Laboratoire de Physique, ENS de Lyon, Foxstream
15:30-15:55 (25min)
› Conditional Sampling with Score-Based Models via Particle Methods
- Stanislas Strasman, Laboratoire de Probabilités, Statistique et Modélisation
15:55-16:20 (25min)
› Selecting informative conformal prediction sets
- Ulysse Gazin, Laboratoire de Probabilités, Statistique et Modélisation
16:20-16:45 (25min)
16:45 - 17:15 (30min)
Coffee break
17:15 - 18:05 (50min)
Predictive posterior sampling from non-stationnary Gaussian process priors via Diffusion models with application to climate data.
Conference room
Gabriel Victorino-Cardoso
18:10 - 19:00 (50min)
TBA
Conference room
Aurélien Bellet
19:30 - 20:30 (1h)
Dinner
7:30 - 8:30 (1h)
Breakfast
8:45 - 9:45 (1h)
Conformal prediction - from a general introduction towards conditional guarantees (3/3)
Conference room
Aymeric Dieuleveut
9:45 - 10:45 (1h)
Transport based generative modeling and applications to sampling (3/3)
Conference room
Marylou Gabrié
10:45 - 11:15 (30min)
Coffee break
11:15 - 11:45 (30min)
Awards & closing speech
Awards & closing speech
12:30 - 13:30 (1h)
Lunch
