Ruediger Urbanke

Tyler Kann, Matthieu R. Bloch, Shrinivas Kudekar et al.

The quantum hashing bound guarantees that rates up to $1-H(p_I, p_X, p_Y, p_Z)$ are achievable for memoryless Pauli channels, but it is not generally tight. A known way to improve achievable rates for certain asymmetric Pauli channels is to apply a small inner stabilizer code to a few channel uses, decode, and treat the resulting logical noise as an induced Pauli channel; reapplying the hashing argument to this induced channel can beat the baseline hashing bound. We generalize this induced-channel viewpoint to arbitrary stabilizer codes used purely as channel transforms. Given any $ [\![ n, k ]\!] $ stabilizer generator set, we construct a full symplectic tableau, compute the induced joint distribution of logical Pauli errors and syndromes under the physical Pauli channel, and obtain an achievable rate via a hashing bound with decoder side information. We perform a structured search over small transforms and report instances that improve the baseline hashing bound for a family of Pauli channels with skewed and independent errors studied in prior work.

Meir Feder, Ruediger Urbanke, Yaniv Fogel

We introduce an information-theoretic framework that views learning as universal prediction under log loss, characterized through regret bounds. Central to the framework is an effective notion of architecture-based model complexity, defined by the probability mass or volume of models in the vicinity of the data-generating process, or its projection on the model class. This volume is related to spectral properties of the expected Hessian or the Fisher Information Matrix, leading to tractable approximations. We argue that successful architectures possess a broad complexity range, enabling learning in highly over-parameterized model classes. The framework sheds light on the role of inductive biases, the effectiveness of stochastic gradient descent, and phenomena such as flat minima. It unifies online, batch, supervised, and generative settings, and applies across the stochastic-realizable and agnostic regimes. Moreover, it provides insights into the success of modern machine-learning architectures, such as deep neural networks and transformers, suggesting that their broad complexity range naturally arises from their layered structure. These insights open the door to the design of alternative architectures with potentially comparable or even superior performance.

Khashayar Barooti, Grzegorz Głuch, Ruediger Urbanke

Modern machine learning systems have been applied successfully to a variety of tasks in recent years but making such systems robust against adversarially chosen modifications of input instances seems to be a much harder problem. It is probably fair to say that no fully satisfying solution has been found up to date and it is not clear if the standard formulation even allows for a principled solution. Hence, rather than following the classical path of bounded perturbations, we consider a model similar to the quantum PAC-learning model introduced by Bshouty and Jackson [1995]. Our first key contribution shows that in this model we can reduce adversarial robustness to the conjunction of two classical learning theory problems, namely (Problem 1) the problem of finding generative models and (Problem 2) the problem of devising classifiers that are robust with respect to distributional shifts. Our second key contribution is that the considered framework does not rely on specific (and hence also somewhat arbitrary) threat models like $\ell_p$ bounded perturbations. Instead, our reduction guarantees that in order to solve the adversarial robustness problem in our model it suffices to consider a single distance notion, i.e. the Hellinger distance. From the technical perspective our protocols are heavily based on the recent advances on delegation of quantum computation, e.g. Mahadev [2018]. Although the considered model is quantum and therefore not immediately applicable to ``real-world'' situations, one might hope that in the future either one can find a way to embed ``real-world'' problems into a quantum framework or that classical algorithms can be found that are capable of mimicking their powerful quantum counterparts.