8 papers
Functional Gradient Descent with Adaptive Representations
Daniel Csillag, Rodrigo Schuller, Pedro Dall'Antonia +3
Functional optimization problems are typically solved by optimizing the parameters of a fixed representation, such as a neural network, resulting in highly nonconvex losses that co…
Random Gradient-Free Optimization in Infinite Dimensional Spaces
Caio Peixoto, Daniel Csillag, Bernardo F. P. da Costa +1
We propose a new gradient-free method for infinite-dimensional optimization in Hilbert spaces that requires only the computation of directional derivatives. Though functional optim…
Avoid What You Know: Divergent Trajectory Balance for GFlowNets
Pedro Dall'Antonia, Tiago da Silva, Daniel Csillag +2
Generative Flow Networks (GFlowNets) are a flexible family of amortized samplers trained to generate discrete and compositional objects with probability proportional to a reward fu…
Image Super-Resolution with Guarantees via Conformalized Generative Models
Eduardo Adame, Daniel Csillag, Guilherme Tegoni Goedert
The increasing use of generative ML foundation models for image restoration tasks such as super-resolution calls for robust and interpretable uncertainty quantification methods. We…
Adaptive Training of INRs via Pruning and Densification
Diana Aldana, João Paulo Lima, Daniel Csillag +4
Encoding input coordinates with sinusoidal functions into multilayer perceptrons (MLPs) has proven effective for implicit neural representations (INRs) of low-dimensional signals,…
Differentially Private E-Values
Daniel Csillag, Diego Mesquita
E-values have gained prominence as flexible tools for statistical inference and risk control, enabling anytime- and post-hoc-valid procedures under minimal assumptions. However, ma…