Accurately evaluating model performance is crucial for deploying machine learning systems in real-world applications. Traditional methods often require a sufficiently large labeled test set to ensure a reliable evaluation. However, in many contexts, a large labeled dataset is costly and labor-intensive. Therefore, we sometimes have to do evaluation by a few labeled samples, which is theoretically challenging. Recent advances in generative models offer a promising alternative by enabling the synthesis of high-quality data. In this work, we make a systematic investigation about the use of synthetic data to estimate the test error of a trained model under limited labeled data conditions. To this end, we develop novel generalization bounds that take synthetic data into account. Those bounds suggest novel ways to optimize synthetic samples for evaluation and theoretically reveal the significant role of the generator's quality. Inspired by those bounds, we propose a theoretically grounded method to generate optimized synthetic data for model evaluation. Experimental results on simulation and tabular datasets demonstrate that, compared to existing baselines, our method achieves accurate and more reliable estimates of the test error.

Motivated by stochastic optimization, we introduce the problem of learning from samples of contextual value distributions. A contextual value distribution can be understood as a family of real-valued distributions, where each sample consists of a context $x$ and a random variable drawn from the corresponding real-valued distribution $D_x$. By minimizing a convex surrogate loss, we learn an empirical distribution $D'_x$ for each context, ensuring a small Lévy distance to $D_x$. We apply this result to obtain the sample complexity bounds for the learning of an $ε$-optimal policy for stochastic optimization problems defined on an unknown contextual value distribution. The sample complexity is shown to be polynomial for the general case of strongly monotone and stable optimization problems, including Single-item Revenue Maximization, Pandora's Box and Optimal Stopping.

This work advances the theoretical understanding of quantum learning by establishing a new family of upper bounds on the expected generalization error of quantum learning algorithms, leveraging the framework introduced by Caro et al. (2024) and a new definition for the expected true loss. Our primary contribution is the derivation of these bounds in terms of quantum and classical Rényi divergences, utilizing a variational approach for evaluating quantum Rényi divergences, specifically the Petz and a newly introduced modified sandwich quantum Rényi divergence. Analytically and numerically, we demonstrate the superior performance of the bounds derived using the modified sandwich quantum Rényi divergence compared to those based on the Petz divergence. Furthermore, we provide probabilistic generalization error bounds using two distinct techniques: one based on the modified sandwich quantum Rényi divergence and classical Rényi divergence, and another employing smooth max Rényi divergence.

We introduce a novel online learning framework that unifies and generalizes pre-established models, such as delayed and corrupted feedback, to encompass adversarial environments where action feedback evolves over time. In this setting, the observed loss is arbitrary and may not correlate with the true loss incurred, with each round updating previous observations adversarially. We propose regret minimization algorithms for both the full-information and bandit settings, with regret bounds quantified by the average feedback accuracy relative to the true loss. Our algorithms match the known regret bounds across many special cases, while also introducing previously unknown bounds.

One of the main theoretical challenges in learning dynamical systems from data is providing upper bounds on the generalization error, that is, the difference between the expected prediction error and the empirical prediction error measured on some finite sample. In machine learning, a popular class of such bounds are the so-called Probably Approximately Correct (PAC) bounds. In this paper, we derive a PAC bound for stable continuous-time linear parameter-varying (LPV) systems. Our bound depends on the H2 norm of the chosen class of the LPV systems, but does not depend on the time interval for which the signals are considered.

This paper is concerned with the consistency analysis on listwise ranking methods. Among various ranking methods, the listwise methods have competitive performances on benchmark datasets and are regarded as one of the state-of-the-art approaches. Most listwise ranking methods manage to optimize ranking on the whole list (permutation) of objects, however, in practical applications such as information retrieval, correct ranking at the top k positions is much more important. This paper aims to analyze whether existing listwise ranking methods are statistically consistent in the top-k setting. For this purpose, we define a top-k ranking framework, where the true loss (and thus the risks) are defined on the basis of top-k subgroup of permutations.

We investigate the local spectral statistics of the loss surface Hessians of artificial neural networks, where we discover excellent agreement with Gaussian Orthogonal Ensemble statistics across several network architectures and datasets. These results shed new light on the applicability of Random Matrix Theory to modelling neural networks and suggest a previously unrecognised role for it in the study of loss surfaces in deep learning. Inspired by these observations, we propose a novel model for the true loss surfaces of neural networks, consistent with our observations, which allows for Hessian spectral densities with rank degeneracy and outliers, extensively observed in practice, and predicts a growing independence of loss gradients as a function of distance in weight-space. We further investigate the importance of the true loss surface in neural networks and find, in contrast to previous work, that the exponential hardness of locating the global minimum has practical consequences for achieving state of the art performance.

This paper is concerned with the consistency analysis on listwise ranking methods. Among various ranking methods, the listwise methods have competitive performances on benchmark datasets and are regarded as one of the state-of-the-art approaches. Most listwise ranking methods manage to optimize ranking on the whole list (permutation) of objects, however, in practical applications such as information retrieval, correct ranking at the top k positions is much more important. This paper aims to analyze whether existing listwise ranking methods are statistically consistent in the top-k setting. For this purpose, we define a top-k ranking framework, where the true loss (and thus the risks) are defined on the basis of top-k subgroup of permutations.

Most machine learning theory and practice is concerned with learning a single task. In this thesis it is argued that in general there is insufficient information in a single task for a learner to generalise well and that what is required for good generalisation is information about many similar learning tasks. Similar learning tasks form a body of prior information that can be used to constrain the learner and make it generalise better. Examples of learning scenarios in which there are many similar tasks are handwritten character recognition and spoken word recognition. The concept of the environment of a learner is introduced as a probability measure over the set of learning problems the learner might be expected to learn. It is shown how a sample from the environment may be used to learn a representation, or recoding of the input space that is appropriate for the environment. Learning a representation can equivalently be thought of as learning the appropriate features of the environment. Bounds are derived on the sample size required to ensure good generalisation from a representation learning process. These bounds show that under certain circumstances learning a representation appropriate for $n$ tasks reduces the number of examples required of each task by a factor of $n$. Once a representation is learnt it can be used to learn novel tasks from the same environment, with the result that far fewer examples are required of the new tasks to ensure good generalisation. Bounds are given on the number of tasks and the number of samples from each task required to ensure that a representation will be a good one for learning novel tasks. The results on representation learning are generalised to cover any form of automated hypothesis space bias.

Probably the most important problem in machine learning is the preliminary biasing of a learner's hypothesis space so that it is small enough to ensure good generalisation from reasonable training sets, yet large enough that it contains a good solution to the problem being learnt. In this paper a mechanism for {\em automatically} learning or biasing the learner's hypothesis space is introduced. It works by first learning an appropriate {\em internal representation} for a learning environment and then using that representation to bias the learner's hypothesis space for the learning of future tasks drawn from the same environment. An internal representation must be learnt by sampling from {\em many similar tasks}, not just a single task as occurs in ordinary machine learning. It is proved that the number of examples $m$ {\em per task} required to ensure good generalisation from a representation learner obeys $m = O(a+b/n)$ where $n$ is the number of tasks being learnt and $a$ and $b$ are constants. If the tasks are learnt independently ({\em i.e.} without a common representation) then $m=O(a+b)$. It is argued that for learning environments such as speech and character recognition $b\gg a$ and hence representation learning in these environments can potentially yield a drastic reduction in the number of examples required per task. It is also proved that if $n = O(b)$ (with $m=O(a+b/n)$) then the representation learnt will be good for learning novel tasks from the same environment, and that the number of examples required to generalise well on a novel task will be reduced to $O(a)$ (as opposed to $O(a+b)$ if no representation is used). It is shown that gradient descent can be used to train neural network representations and experiment results are reported providing strong qualitative support for the theoretical results.