3 citations · 4 across the 17 of their papers we have counts for
8 papers · 1 filter
Beyond Optimal Rates in Stochastic Optimization: Trajectory-Adaptive Stopping Rules
Liviu Aolaritei, Lucas Lévy, Francis Bach +1
Stochastic gradient descent (SGD) is typically analyzed at a deterministic horizon chosen before the algorithm is run, even though practical stopping decisions are made adaptively…
Eigenvalue Calibration for Semantic Embeddings of Large Language Models
Sebastian G. Gruber, Nassim Walha, Francis Bach +1
Uncertainty quantification is central to the reliable deployment of large language models (LLMs), and eigenvalues of semantic embeddings have recently emerged as a key tool in stat…
DecompRL: Solving Harder Problems by Learning Modular Code Generation
Juliette Decugis, Fabian Gloeckle, Francis Bach +2
How can Large Language Models (LLMs) solve problems they currently cannot? Repeated sampling scales test-time compute but GPU cost grows linearly with attempts, while reinforcement…
CalArena: A Large-Scale Post-Hoc Calibration Benchmark
Eugène Berta, David Holzmüller, Francis Bach +1
Reliable probability estimates are critical in many machine learning applications, yet modern classifiers are often poorly calibrated. Post-hoc calibration provides a simple and wi…
Explaining and Preventing Alignment Collapse in Iterative RLHF
Etienne Gauthier, Francis Bach, Michael I. Jordan
Reinforcement learning from human feedback (RLHF) typically assumes a static or non-strategic reward model (RM). In iterative deployment, however, the policy generates the data on…
Structured Matrix Scaling for Multi-Class Calibration
Eugène Berta, David Holzmüller, Michael I. Jordan +1
Post-hoc recalibration methods are widely used to ensure that classifiers provide faithful probability estimates. We argue that parametric recalibration functions based on logistic…
Rethinking Early Stopping: Refine, Then Calibrate
Eugène Berta, David Holzmüller, Michael I. Jordan +1
Machine learning classifiers often produce probabilistic predictions that are critical for accurate and interpretable decision-making in various domains. The quality of these predi…
Classifier Calibration with ROC-Regularized Isotonic Regression
Eugene Berta, Francis Bach, Michael Jordan
Calibration of machine learning classifiers is necessary to obtain reliable and interpretable predictions, bridging the gap between model confidence and actual probabilities. One p…