Related papers: Optimal Protocols for Nonlocality Distillation
Deep neural networks (DNNs) have achieved tremendous success in many tasks of machine learning, such as the image classification. Unfortunately, researchers have shown that DNNs are easily attacked by adversarial examples, slightly…
Dataset distillation is an advanced technique aimed at compressing datasets into significantly smaller counterparts, while preserving formidable training performance. Significant efforts have been devoted to promote evaluation accuracy…
Deep regression trackers are among the fastest tracking algorithms available, and therefore suitable for real-time robotic applications. However, their accuracy is inadequate in many domains due to distribution shift and overfitting. In…
We develop theory for nonlinear dimensionality reduction (NLDR). A number of NLDR methods have been developed, but there is limited understanding of how these methods work and the relationships between them. There is limited basis for using…
Nonlocality is a quintessential signature of nonclassical behaviour and a resource for quantum advantages in communication and computation. The paradoxical correlations witnessed by strong nonlocality undergird the standard probabilistic…
We show that the maximum fidelity obtained by a p.p.t. distillation protocol is given by the solution to a certain semidefinite program. This gives a number of new lower and upper bounds on p.p.t. distillable entanglement (and thus new…
Non-local methods exploiting the self-similarity of natural signals have been well studied, for example in image analysis and restoration. Existing approaches, however, rely on k-nearest neighbors (KNN) matching in a fixed feature space.…
Nonlocal boxes are conceptual tools that capture the essence of the phenomenon of quantum non-locality, central to modern quantum theory and quantum technologies. We introduce network nonlocal boxes tailored for quantum networks under the…
We consider an experiment with two qualitative factors at 2 levels each and a binary response, that follows a generalized linear model. In Mandal, Yang and Majumdar (2010) we obtained basic results and characterizations of locally D-optimal…
Recently, it was demonstrated in [CS2012,CS2013] that the robustness of the classical Non-Local Means (NLM) algorithm [BCM2005] can be improved by incorporating $\ell^p (0 < p \leq 2)$ regression into the NLM framework. This general…
The development of efficient sampling algorithms catering to non-Euclidean geometries has been a challenging endeavor, as discretization techniques which succeed in the Euclidean setting do not readily carry over to more general settings.…
Quantum theory puts forward phenomena unexplainable by classical physics - or information, for that matter. A prominent example is non-locality. Non-local correlations cannot be explained, in classical terms, by shared information but only…
Reinforcement learning (RL) can be used to improve the policy (denoiser) of diffusion large language models (dLLMs), while being hindered by the intractability of the policy likelihood. A dominant and efficient family of methods replaces…
Most deep learning frameworks require users to pool their local data or model updates to a trusted server to train or maintain a global model. The assumption of a trusted server who has access to user information is ill-suited in many…
We present a security proof for establishing private entanglement by means of recurrence-type entanglement distillation protocols over noisy quantum channels. We consider protocols where the local devices are imperfect, and show that…
It is well known that the Johnson-Lindenstrauss dimensionality reduction method is optimal for worst case distortion. While in practice many other methods and heuristics are used, not much is known in terms of bounds on their performance.…
Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on…
Learning from noisy data has become essential for adapting deep learning models to real-world applications. Traditional methods often involve first evaluating the noise and then applying strategies such as discarding noisy samples,…
Nonlocality and quantum entanglement constitute two special aspects of the quantum correlations existing in quantum systems, which are of paramount importance in quantum-information theory. Traditionally, they have been regarded as…
We develop adaptive discretization algorithms for locally optimal experimental design of nonlinear prediction models. With these algorithms, we refine and improve a pertinent state-of-the-art algorithm in various respects. We establish…