Perturbing the Derivative: Wild Refitting for Model-Free Evaluation of Machine Learning Models under Bregman Losses

• URL: http://arxiv.org/abs/2509.02476v6
• Date: Tue, 04 Nov 2025 02:23:18 GMT
• Title: Perturbing the Derivative: Wild Refitting for Model-Free Evaluation of Machine Learning Models under Bregman Losses
• Authors: Haichen Hu, David Simchi-Levi,
• Abstract summary: We show that one can efficiently upper bound the excess risk through the so-called "wild optimism"<n>Unlike conventional analysis, our framework operates with just one dataset and black-box access to the training procedure.<n>Our work is promising for theoretically evaluating modern opaque ML models, such as deep neural networks and generative models.
• Score: 15.386375612838371
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study the excess risk evaluation of classical penalized empirical risk minimization (ERM) with Bregman losses. We show that by leveraging the idea of wild refitting, one can efficiently upper bound the excess risk through the so-called "wild optimism," without relying on the global structure of the underlying function class. This property makes our approach inherently model-free. Unlike conventional analysis, our framework operates with just one dataset and black-box access to the training procedure. The method involves randomized Rademacher symmetrization and constructing artificially modified outputs by perturbation in the derivative space with appropriate scaling, upon which we retrain a second predictor for excess risk estimation. We establish high-probability performance guarantees both under the fixed design setting and the random design setting, demonstrating that wild refitting under Bregman losses, with an appropriately chosen wild noise scale, yields a valid upper bound on the excess risk. Thus, our work is promising for theoretically evaluating modern opaque ML models, such as deep neural networks and generative models, where the function class is too complex for classical learning theory and empirical process techniques.

Related papers

• Robust Bayesian Dynamic Programming for On-policy Risk-sensitive Reinforcement Learning [4.71677151409532]
  We propose a novel framework for risk-sensitive reinforcement learning that incorporates robustness against transition uncertainty.<n>Our framework unifies and generalizes most existing RL frameworks by permitting general coherent risk measures for both inner and outer risk measures.
  arXiv  Detail & Related papers  (2025-12-31T03:13:22Z)
• Worst-case generation via minimax optimization in Wasserstein space [19.645939141861543]
  Worst-case generation plays a critical role in evaluating robustness and stress-testing systems under distribution shifts.<n>We develop a generative modeling framework for worst-case generation for a pre-specified risk.
  arXiv  Detail & Related papers  (2025-12-09T02:11:08Z)
• Doubly Wild Refitting: Model-Free Evaluation of High Dimensional Black-Box Predictions under Convex Losses [15.386375612838371]
  We study the problem of excess risk evaluation for empirical risk minimization under general convex loss functions.<n>Our contribution is an efficient refitting procedure that computes the excess risk and provides high-probability upper bounds under the fixed-design setting.
  arXiv  Detail & Related papers  (2025-11-24T05:38:47Z)
• Risk-aware Direct Preference Optimization under Nested Risk Measure [23.336246526648374]
  Risk-aware Direct Preference Optimization (Ra-DPO) is a novel approach that incorporates risk-awareness by employing a class of nested risk measures.<n> Experimental results across three open-source datasets demonstrate the proposed method's superior performance in balancing alignment performance and model drift.
  arXiv  Detail & Related papers  (2025-05-26T08:01:37Z)
• Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing [58.52119063742121]
  Retraining a model using its own predictions together with the original, potentially noisy labels is a well-known strategy for improving the model performance.<n>This paper addresses the question of how to optimally combine the model's predictions and the provided labels.<n>Our main contribution is the derivation of the Bayes optimal aggregator function to combine the current model's predictions and the given labels.
  arXiv  Detail & Related papers  (2025-05-21T07:16:44Z)
• Risk-Averse Certification of Bayesian Neural Networks [70.44969603471903]
  We propose a Risk-Averse Certification framework for Bayesian neural networks called RAC-BNN.<n>Our method leverages sampling and optimisation to compute a sound approximation of the output set of a BNN.<n>We validate RAC-BNN on a range of regression and classification benchmarks and compare its performance with a state-of-the-art method.
  arXiv  Detail & Related papers  (2024-11-29T14:22:51Z)
• Bayesian Nonparametrics Meets Data-Driven Distributionally Robust Optimization [29.24821214671497]
  Training machine learning and statistical models often involve optimizing a data-driven risk criterion. We propose a novel robust criterion by combining insights from Bayesian nonparametric (i.e., Dirichlet process) theory and a recent decision-theoretic model of smooth ambiguity-averse preferences. For practical implementation, we propose and study tractable approximations of the criterion based on well-known Dirichlet process representations.
  arXiv  Detail & Related papers  (2024-01-28T21:19:15Z)
• Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization [59.758009422067]
  We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning. We propose a new uncertainty Bellman equation (UBE) whose solution converges to the true posterior variance over values. We introduce a general-purpose policy optimization algorithm, Q-Uncertainty Soft Actor-Critic (QU-SAC) that can be applied for either risk-seeking or risk-averse policy optimization.
  arXiv  Detail & Related papers  (2023-12-07T15:55:58Z)
• Outlier-robust neural network training: variation regularization meets trimmed loss to prevent functional breakdown [2.5628953713168685]
  We tackle the challenge of outlier-robust predictive modeling using highly expressive neural networks.<n>Our approach integrates two key components: (1) a transformed trimmed loss (TTL), and (2) higher-order variation regularization (HOVR), which imposes smoothness constraints on the prediction function.
  arXiv  Detail & Related papers  (2023-08-04T12:57:13Z)
• Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior [51.60683890503293]
  We propose a theoretical framework for studying behavior cloning of complex expert demonstrations using generative modeling. We show that pure supervised cloning can generate trajectories matching the per-time step distribution of arbitrary expert trajectories.
  arXiv  Detail & Related papers  (2023-07-27T04:27:26Z)
• When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning [62.00672284480755]
  This paper aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent. Accurate models of expertise in executing a task has applications in safety-sensitive applications such as clinical decision making and autonomous driving.
  arXiv  Detail & Related papers  (2023-02-15T04:14:20Z)
• GEC: A Unified Framework for Interactive Decision Making in MDP, POMDP, and Beyond [101.5329678997916]
  We study sample efficient reinforcement learning (RL) under the general framework of interactive decision making. We propose a novel complexity measure, generalized eluder coefficient (GEC), which characterizes the fundamental tradeoff between exploration and exploitation. We show that RL problems with low GEC form a remarkably rich class, which subsumes low Bellman eluder dimension problems, bilinear class, low witness rank problems, PO-bilinear class, and generalized regular PSR.
  arXiv  Detail & Related papers  (2022-11-03T16:42:40Z)
• Learning Dynamical Systems via Koopman Operator Regression in Reproducing Kernel Hilbert Spaces [52.35063796758121]
  We formalize a framework to learn the Koopman operator from finite data trajectories of the dynamical system. We link the risk with the estimation of the spectral decomposition of the Koopman operator. Our results suggest RRR might be beneficial over other widely used estimators.
  arXiv  Detail & Related papers  (2022-05-27T14:57:48Z)
• Mitigating multiple descents: A model-agnostic framework for risk monotonization [84.6382406922369]
  We develop a general framework for risk monotonization based on cross-validation. We propose two data-driven methodologies, namely zero- and one-step, that are akin to bagging and boosting.
  arXiv  Detail & Related papers  (2022-05-25T17:41:40Z)
• Safe Continuous Control with Constrained Model-Based Policy Optimization [0.0]
  We introduce a model-based safe exploration algorithm for constrained high-dimensional control. We also introduce a practical algorithm that accelerates policy search with model-generated data.
  arXiv  Detail & Related papers  (2021-04-14T15:20:55Z)
• Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature [61.22680308681648]
  We show that global convergence is statistically intractable even for one-layer neural net bandit with a deterministic reward. For both nonlinear bandit and RL, the paper presents a model-based algorithm, Virtual Ascent with Online Model Learner (ViOL)
  arXiv  Detail & Related papers  (2021-02-08T12:41:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.