10 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…
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…
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…
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…
Extending Prediction-Powered Inference through Conformal Prediction
Daniel Csillag, Pedro Dall'Antonia, Claudio José Struchiner +1
Prediction-powered inference is a recent methodology for the safe use of black-box ML models to impute missing data, strengthening inference of statistical parameters. However, man…
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…
Prediction-Powered E-Values
Daniel Csillag, Claudio José Struchiner, Guilherme Tegoni Goedert
Quality statistical inference requires a sufficient amount of data, which can be missing or hard to obtain. To this end, prediction-powered inference has risen as a promising metho…
Strategic Conformal Prediction
Daniel Csillag, Claudio José Struchiner, Guilherme Tegoni Goedert
When a machine learning model is deployed, its predictions can alter its environment, as better informed agents strategize to suit their own interests. With such alterations in min…
Generalization Bounds for Causal Regression: Insights, Guarantees and Sensitivity Analysis
Daniel Csillag, Claudio José Struchiner, Guilherme Tegoni Goedert
Many algorithms have been recently proposed for causal machine learning. Yet, there is little to no theory on their quality, especially considering finite samples. In this work, we…