Learning populations of preferences via pairwise comparison queries
G Tatli, Y Chen, RK Vinayak - International Conference on …, 2024 - proceedings.mlr.press
Ideal point based preference learning using pairwise comparisons of type" Do you prefer a
or b?" has emerged as a powerful tool for understanding how we make preferences. Existing …
or b?" has emerged as a powerful tool for understanding how we make preferences. Existing …
Linear label ranking with bounded noise
D Fotakis, A Kalavasis, V Kontonis… - Advances in Neural …, 2022 - proceedings.neurips.cc
Label Ranking (LR) is the supervised task of learning a sorting function that maps feature
vectors $ x\in\mathbb {R}^ d $ to rankings $\sigma (x)\in\mathbb S_k $ over a finite set of $ k …
vectors $ x\in\mathbb {R}^ d $ to rankings $\sigma (x)\in\mathbb S_k $ over a finite set of $ k …
Robust voting rules from algorithmic robust statistics
Maximum likelihood estimation furnishes powerful insights into voting theory, and the design
of voting rules. However the MLE can usually be badly corrupted by a single outlying …
of voting rules. However the MLE can usually be badly corrupted by a single outlying …
Sharp analysis of EM for learning mixtures of pairwise differences
We consider a symmetric mixture of linear regressions with random samples from the
pairwise comparison design, which can be seen as a noisy version of a type of Euclidean …
pairwise comparison design, which can be seen as a noisy version of a type of Euclidean …
Mallows-DPO: Fine-Tune Your LLM with Preference Dispersions
Direct Preference Optimization (DPO) has recently emerged as a popular approach to
improve reinforcement learning with human feedback (RLHF), leading to better techniques …
improve reinforcement learning with human feedback (RLHF), leading to better techniques …
[图书][B] Learning From Imperfect Data: Noisy Labels, Truncation, and Coarsening
V Kontonis - 2023 - search.proquest.com
The datasets used in machine learning and statistics are huge and often imperfect, eg, they
contain corrupted data, examples with wrong labels, or hidden biases. Most existing …
contain corrupted data, examples with wrong labels, or hidden biases. Most existing …
[PDF][PDF] Algorithm Design for Reliable Machine Learning
A Kalavasis - 2023 - dspace.lib.ntua.gr
In this thesis we theoretically study questions in the area of Reliable Machine Learning in
order to design algorithms that are robust to bias and noise (Robust Machine Learning) and …
order to design algorithms that are robust to bias and noise (Robust Machine Learning) and …