1 citations · 1 across the 17 of their papers we have counts for
19 papers
Deterministic Bounds on Accuracy and Stability of Metric-Space Regression and Classification
Nina Maria Gottschling, Jakob Gawlikowski, Michele Caprio
Data-driven approaches often face ambiguity in datasets due to sensor or target noise, insufficient information, and noise in the input data. While best-fit machine learning method…
Subjective Risk Decomposition: A New View for Uncertainty Quantification
Raghad Alamri, Michele Caprio, Gavin Brown
We present a novel viewpoint for uncertainty quantification. Uncertainty measures are not primitives, in need of axioms and argumentation, but instead consequences, of higher-level…
Self-Supervised Laplace Approximation for Bayesian Uncertainty Quantification
Julian Rodemann, Alexander Marquard, Thomas Augustin +1
Approximate Bayesian inference typically revolves around computing the posterior parameter distribution. In practice, however, the main object of interest is often a model's predic…
Decoupled Conformal Optimisation: Efficient Prediction Sets via Independent Tuning and Calibration
Fanyi Wu, Lihua Niu, Samuel Kaski +1
Bayesian conformal optimisation methods often use the same held-out data both to search for efficient prediction sets and to certify coverage or risk. This coupling is natural for…
CREDO: Epistemic-Aware Conformalized Credal Envelopes for Regression
Luben M. C. Cabezas, Sabina J. Sloman, Bruno M. Resende +3
Conformal prediction delivers prediction intervals with distribution-free coverage, but its intervals can look overconfident in regions where the model is extrapolating, because st…
Quantification of Credal Uncertainty: A Distance-Based Approach
Xabier Gonzalez-Garcia, Siu Lun Chau, Julian Rodemann +6
Credal sets, i.e., closed convex sets of probability measures, provide a natural framework to represent aleatoric and epistemic uncertainty in machine learning. Yet how to quantify…
Verbalizing LLM's Higher-order Uncertainty via Imprecise Probabilities
Anita Yang, Krikamol Muandet, Michele Caprio +2
Despite the growing demand for eliciting uncertainty from large language models (LLMs), empirical evidence suggests that LLM behavior is not always adequately captured by the elici…
Hoeffding-Type Concentration Bounds for Exchangeable Random Variables
Nina Maria Gottschling, Michele Caprio
We establish Hoeffding-type concentration inequalities for empirical means of bounded infinitely exchangeable sequences. Using the unique de Finetti mixing measure, we identify the…
Robust Predictive Uncertainty and Double Descent in Contaminated Bayesian Random Features
Michele Caprio, Katerina Papagiannouli, Siu Lun Chau +1
We propose a robust Bayesian formulation of random feature (RF) regression that accounts explicitly for prior and likelihood misspecification via Huber-style contamination sets. St…
Bayesian Conformal Prediction as a Decision Risk Problem
Fanyi Wu, Veronika Lohmanova, Samuel Kaski +1
We propose Bayesian Conformal Prediction (BCP), a framework that combines Bayesian posterior predictive distributions with PAC-style conformal risk control to produce prediction se…
Bulk-Calibrated Credal Ambiguity Sets: Fast, Tractable Decision Making under Out-of-Sample Contamination
Mengqi Chen, Thomas B. Berrett, Theodoros Damoulas +1
Distributionally robust optimisation (DRO) minimises the worst-case expected loss over an ambiguity set that can capture distributional shifts in out-of-sample environments. While…
Credal and Interval Deep Evidential Classifications
Michele Caprio, Shireen K. Manchingal, Fabio Cuzzolin
Uncertainty Quantification (UQ) presents a pivotal challenge in the field of Artificial Intelligence (AI), profoundly impacting decision-making, risk assessment and model reliabili…
Conformal Prediction Regions are Imprecise Highest Density Regions
Michele Caprio, Yusuf Sale, Eyke Hüllermeier
Recently, Cella and Martin proved how, under an assumption called consonance, a credal set (i.e. a closed and convex set of probabilities) can be derived from the conformal transdu…
Conformalized Credal Regions for Classification with Ambiguous Ground Truth
Michele Caprio, David Stutz, Shuo Li +1
An open question in \emph{Imprecise Probabilistic Machine Learning} is how to empirically derive a credal region (i.e., a closed and convex family of probabilities on the output sp…
Optimal Transport for -Contaminated Credal Sets: To the Memory of Sayan Mukherjee
Michele Caprio
We present generalized versions of Monge's and Kantorovich's optimal transport problems with the probabilities being transported replaced by lower probabilities. We show that, when…
Imprecise Markov Semigroups and their Ergodicity
Michele Caprio, Mengqi Chen
We introduce the concept of an imprecise Markov semigroup \(\mathbf Q\). It is a tool that allows us to represent ambiguity around both the transition probabilities and the invaria…
Credal Learning Theory
Michele Caprio, Maryam Sultana, Eleni Elia +1
Statistical learning theory is the foundation of machine learning, providing theoretical bounds for the risk of models learned from a (single) training set, assumed to issue from a…
Second-Order Uncertainty Quantification: A Distance-Based Approach
Yusuf Sale, Viktor Bengs, Michele Caprio +1
In the past couple of years, various approaches to representing and quantifying different types of predictive uncertainty in machine learning, notably in the setting of classificat…
IBCL: Zero-shot Model Generation under Stability-Plasticity Trade-offs
Pengyuan Lu, Michele Caprio, Eric Eaton +1
Algorithms that balance the stability-plasticity trade-off are well studied in the Continual Learning literature. However, only a few focus on obtaining models for specified trade-…