Refined Risk Bounds for Unbounded Losses via Transductive Priors

Дата публикации: 17-08-2026 20:26:00

We revisit the sequential variants of linear regression with the squared loss, classification problems with hinge loss, and logistic regression, all characterized by unbounded losses in the setup where no assumptions are made on the magnitude of design vectors and the norm of the optimal vector of parameters. The key distinction from existing results lies in our assumption that the set of design vectors is known in advance (though their order is not), a setup sometimes referred to as transductive online learning. While this assumption might seem similar to fixed design regression or denoising, we demonstrate that the sequential nature of our algorithms allows us to convert our bounds into statistical ones with random design without making any additional assumptions about the distribution of the design vectors-an impossibility for standard denoising results. Our key tools are based on the exponential weights algorithm with carefully chosen transductive (design-dependent) priors, which exploit the full horizon of the design vectors, as well as additional aggregation tools that address the possibly unbounded norm of the vector of the optimal solution.
Our classification regret bounds have a feature that is only attributed to bounded losses in the literature: they depend solely on the dimension of the parameter space and on the number of rounds, independent of the design vectors or the norm of the optimal solution. For linear regression with squared loss, we further extend our analysis to the sparse case, providing sparsity regret bounds that depend additionally only on the magnitude of the response variables. We argue that these improved bounds are specific to the transductive setting and unattainable in the worst-case sequential setup.
Our algorithms, in several cases, have polynomial-time approximations and reduce to sampling with respect to log-concave measures instead of aggregating over hard-to-construct epsilon-covers of classes.

Схожие новости

#	Наименование новости	Тональность	Информативность	Дата публикации
1	Inference with non-differentiable surrogate loss in a general high-dimensional classification framework	0	8.38	17-08-2026
2	Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes	0	7.52	17-08-2026
3	Mixing times of data-augmentation Gibbs samplers for high-dimensional probit regression	0	8.78	17-08-2026
4	Near-optimal Delta-convex Estimation of Lipschitz Functions	0	9.71	17-08-2026
5	Semi-supervised learning for linear extremile regression	0	6.83	17-08-2026
6	Asymptotics of Stochastic Gradient Descent with Dropout Regularization in Linear Models	0	5.86	17-08-2026
7	Transfer Learning via Regularized Random-effects Linear Discriminant Analysis	0	5.98	17-08-2026
8	Transfer Conformal Predictive Inference for Regression	0	5.02	17-08-2026
9	Best Arm Identification with Minimal Regret	0	8.4	17-08-2026
10	Classification Under Local Differential Privacy with Model Reversal and Model Averaging	0	3.84	17-08-2026

Классификация: . Схожих патентов: 0. Схожих новостей: 10. Тональность: 0. Информативность: 5.33. Источник: jmlr.org.