Zobrazeno 1 - 10
of 4 358
pro vyhledávání: '"risk bounds"'
The sharpest known high probability excess risk bounds are up to $O\left( 1/n \right)$ for empirical risk minimization and projected gradient descent via algorithmic stability (Klochkov \& Zhivotovskiy, 2021). In this paper, we show that high probabi
Externí odkaz:
http://arxiv.org/abs/2410.09766
Minimax problems have achieved success in machine learning such as adversarial training, robust optimization, reinforcement learning. For theoretical analysis, current optimal excess risk bounds, which are composed by generalization error and optimiz
Externí odkaz:
http://arxiv.org/abs/2410.08497
The predict-then-optimize (PTO) framework is indispensable for addressing practical stochastic decision-making tasks. It consists of two crucial steps: initially predicting unknown parameters of an optimization model and subsequently solving the prob
Externí odkaz:
http://arxiv.org/abs/2411.12653
Recurrent Neural Networks (RNNs) have achieved great success in the prediction of sequential data. However, their theoretical studies are still lagging behind because of their complex interconnected structures. In this paper, we establish a new gener
Externí odkaz:
http://arxiv.org/abs/2411.02784
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 desi
Externí odkaz:
http://arxiv.org/abs/2410.21621
In this work, we provide upper bounds on the risk of mixtures of experts by imposing local differential privacy (LDP) on their gating mechanism. These theoretical guarantees are tailored to mixtures of experts that utilize the one-out-of-$n$ gating m
Externí odkaz:
http://arxiv.org/abs/2410.10397
Autor:
Mai, The Tien
PAC-Bayesian bounds have proven to be a valuable tool for deriving generalization bounds and for designing new learning algorithms in machine learning. However, it typically focus on providing generalization bounds with respect to a chosen loss funct
Externí odkaz:
http://arxiv.org/abs/2408.08675
To investigate the theoretical foundations of deep learning from the viewpoint of the minimum description length (MDL) principle, we analyse risk bounds of MDL estimators based on two-stage codes for simple two-layers neural networks (NNs) with ReLU
Externí odkaz:
http://arxiv.org/abs/2407.03854
Autor:
Spokoiny, Vladimir
This note extends the results of classical parametric statistics like Fisher and Wilks theorem to modern setups with a high or infinite parameter dimension, limited sample size, and possible model misspecification. We consider a special class of stoc
Externí odkaz:
http://arxiv.org/abs/2404.14227
We consider the problem of estimating probability density functions based on sample data, using a finite mixture of densities from some component class. To this end, we introduce the $h$-lifted Kullback--Leibler (KL) divergence as a generalization of
Externí odkaz:
http://arxiv.org/abs/2404.12586