The ultimate goal of any sparse coding method is to accurately recover from a few noisy linear measurements, an unknown sparse vector. Unfortunately, this estimation problem is NP-hard in general, and it is therefore always approached with an approximation method, such as lasso or orthogonal matching pursuit, thus trading off accuracy for less computational complexity. In this paper, we develop a quantum-inspired algorithm for sparse coding, with the premise that the emergence of quantum computers and Ising machines can potentially lead to more accurate estimations compared to classical approximation methods. To this end, we formulate the most general sparse coding problem as a quadratic unconstrained binary optimization (QUBO) task, which can be efficiently minimized using quantum technology. To derive at a QUBO model that is also efficient in terms of the number of spins (space complexity), we separate our analysis into three different scenarios. These are defined by the number of bits required to express the underlying sparse vector: binary, 2-bit, and a general fixed-point representation. We conduct numerical experiments with simulated data on LightSolver's quantum-inspired digital platform to verify the correctness of our QUBO formulation and to demonstrate its advantage over baseline methods.
相關內容
In this paper, we present Q# implementations for arbitrary single-variabled fixed-point arithmetic operations for a gate-based quantum computer based on lookup tables (LUTs). In general, this is an inefficent way of implementing a function since the number of inputs can be large or even infinite. However, if the input domain can be bounded and there can be some error tolerance in the output (both of which are often the case in practical use-cases), the quantum LUT implementation of certain quantum arithmetic functions can be more efficient than their corresponding reversible arithmetic implementations. We discuss the implementation of the LUT using Q\# and its approximation errors. We then show examples of how to use the LUT to implement quantum arithmetic functions and compare the resources required for the implementation with the current state-of-the-art bespoke implementations of some commonly used arithmetic functions. The implementation of the LUT is designed for use by practitioners to use when implementing end-to-end quantum algorithms. In addition, given its well-defined approximation errors, the LUT implementation makes for a clear benchmark for evaluating the efficiency of bespoke quantum arithmetic circuits .
The inadvertent stealing of private/sensitive information using Knowledge Distillation (KD) has been getting significant attention recently and has guided subsequent defense efforts considering its critical nature. Recent work Nasty Teacher proposed to develop teachers which can not be distilled or imitated by models attacking it. However, the promise of confidentiality offered by a nasty teacher is not well studied, and as a further step to strengthen against such loopholes, we attempt to bypass its defense and steal (or extract) information in its presence successfully. Specifically, we analyze Nasty Teacher from two different directions and subsequently leverage them carefully to develop simple yet efficient methodologies, named as HTC and SCM, which increase the learning from Nasty Teacher by upto 68.63% on standard datasets. Additionally, we also explore an improvised defense method based on our insights of stealing. Our detailed set of experiments and ablations on diverse models/settings demonstrate the efficacy of our approach.
A good estimation of the actions' cost is key in task planning for human-robot collaboration. The duration of an action depends on agents' capabilities and the correlation between actions performed simultaneously by the human and the robot. This paper proposes an approach to learning actions' costs and coupling between actions executed concurrently by humans and robots. We leverage the information from past executions to learn the average duration of each action and a synergy coefficient representing the effect of an action performed by the human on the duration of the action performed by the robot (and vice versa). We implement the proposed method in a simulated scenario where both agents can access the same area simultaneously. Safety measures require the robot to slow down when the human is close, denoting a bad synergy of tasks operating in the same area. We show that our approach can learn such bad couplings so that a task planner can leverage this information to find better plans.
In group testing, the goal is to identify a subset of defective items within a larger set of items based on tests whose outcomes indicate whether at least one defective item is present. This problem is relevant in areas such as medical testing, DNA sequencing, communication protocols, and many more. In this paper, we study (i) a sparsity-constrained version of the problem, in which the testing procedure is subjected to one of the following two constraints: items are finitely divisible and thus may participate in at most $\gamma$ tests; or tests are size-constrained to pool no more than $\rho$ items per test; and (ii) a noisy version of the problem, where each test outcome is independently flipped with some constant probability. Under each of these settings, considering the for-each recovery guarantee with asymptotically vanishing error probability, we introduce a fast splitting algorithm and establish its near-optimality not only in terms of the number of tests, but also in terms of the decoding time. While the most basic formulations of our algorithms require $\Omega(n)$ storage for each algorithm, we also provide low-storage variants based on hashing, with similar recovery guarantees.
High-value payment systems (HVPS) are typically liquidity-intensive as the payment requests are indivisible and settled on a gross basis. Finding the right order in which payments should be processed to maximize the liquidity efficiency of these systems is an $NP$-hard combinatorial optimization problem, which quantum algorithms may be able to tackle at meaningful scales. We developed an algorithm and ran it on a hybrid quantum annealing solver to find an ordering of payments that reduced the amount of system liquidity necessary without substantially increasing payment delays. Despite the limitations in size and speed of today's quantum computers, our algorithm provided quantifiable efficiency improvements when applied to the Canadian HVPS using a 30-day sample of transaction data. By reordering each batch of 70 payments as they entered the queue, we achieved an average of C\$240 million in daily liquidity savings, with a settlement delay of approximately 90 seconds. For a few days in the sample, the liquidity savings exceeded C\$1 billion. This algorithm could be incorporated as a centralized preprocessor into existing HVPS without entailing a fundamental change to their risk management models.
The use of quantum computation for wireless network applications is emerging as a promising paradigm to bridge the performance gap between in-practice and optimal wireless algorithms. While today's quantum technology offers limited number of qubits and low fidelity gates, application-based quantum solutions help us to understand and improve the performance of such technology even further. This paper introduces QGateD-Polar, a novel Quantum Gate-based Maximum-Likelihood Decoder design for Polar error correction codes, which are becoming widespread in today's 5G and tomorrow's NextG wireless networks. QGateD-Polar uses quantum gates to dictate the time evolution of Polar code decoding -- from the received wireless soft data to the final decoded solution -- by leveraging quantum phenomena such as superposition, entanglement, and interference, making it amenable to quantum gate-based computers. Our early results show that QGateD-Polar achieves the Maximum Likelihood performance in ideal quantum simulations, demonstrating how performance varies with noise.
The broad adoption of the Internet of Things during the last decade has widened the application horizons of distributed sensor networks, ranging from smart home appliances to automation, including remote sensing. Typically, these distributed systems are composed of several nodes attached to sensing devices linked by a heterogeneous communication network. The unreliable nature of these systems (e.g., devices might run out of energy or communications might become unavailable) drives practitioners to implement heavyweight fault tolerance mechanisms to identify those untrustworthy nodes that are misbehaving erratically and, thus, ensure that the sensed data from the IoT domain are correct. The overhead in the communication network degrades the overall system, especially in scenarios with limited available bandwidth that are exposed to severely harsh conditions. Quantum Internet might be a promising alternative to minimize traffic congestion and avoid worsening reliability due to the link saturation effect by using a quantum consensus layer. In this regard, the purpose of this paper is to explore and simulate the usage of quantum consensus architecture in one of the most challenging natural environments in the world where researchers need a responsive sensor network: the remote sensing of permafrost in Antarctica. More specifically, this paper 1) describes the use case of permafrost remote sensing in Antarctica, 2) proposes the usage of a quantum consensus management plane to reduce the traffic overhead associated with fault tolerance protocols, and 3) discusses, by means of simulation, possible improvements to increase the trustworthiness of a holistic telemetry system by exploiting the complexity reduction offered by the quantum parallelism. Collected insights from this research can be generalized to current and forthcoming IoT environments.
The field of quantum machine learning (QML) explores how quantum computers can be used to more efficiently solve machine learning problems. As an application of hybrid quantum-classical algorithms, it promises a potential quantum advantages in the near term. In this thesis, we use the ZXW-calculus to diagrammatically analyse two key problems that QML applications face. First, we discuss algorithms to compute gradients on quantum hardware that are needed to perform gradient-based optimisation for QML. Concretely, we give new diagrammatic proofs of the common 2- and 4-term parameter shift rules used in the literature. Additionally, we derive a novel, generalised parameter shift rule with 2n terms that is applicable to gates that can be represented with n parametrised spiders in the ZXW-calculus. Furthermore, to the best of our knowledge, we give the first proof of a conjecture by Anselmetti et al. by proving a no-go theorem ruling out more efficient alternatives to the 4-term shift rule. Secondly, we analyse the gradient landscape of quantum ans\"atze for barren plateaus using both empirical and analytical techniques. Concretely, we develop a tool that automatically calculates the variance of gradients and use it to detect likely barren plateaus in commonly used quantum ans\"atze. Furthermore, we formally prove the existence or absence of barren plateaus for a selection of ans\"atze using diagrammatic techniques from the ZXW-calculus.
We study the following two fixed-cardinality optimization problems (a maximization and a minimization variant). For a fixed $\alpha$ between zero and one we are given a graph and two numbers $k \in \mathbb{N}$ and $t \in \mathbb{Q}$. The task is to find a vertex subset $S$ of exactly $k$ vertices that has value at least (resp. at most for minimization) $t$. Here, the value of a vertex set computes as $\alpha$ times the number of edges with exactly one endpoint in $S$ plus $1-\alpha$ times the number of edges with both endpoints in $S$. These two problems generalize many prominent graph problems, such as Densest $k$-Subgraph, Sparsest $k$-Subgraph, Partial Vertex Cover, and Max ($k$,$n-k$)-Cut. In this work, we complete the picture of their parameterized complexity on several types of sparse graphs that are described by structural parameters. In particular, we provide kernelization algorithms and kernel lower bounds for these problems. A somewhat surprising consequence of our kernelizations is that Partial Vertex Cover and Max $(k,n-k)$-Cut not only behave in the same way but that the kernels for both problems can be obtained by the same algorithms.
Since deep neural networks were developed, they have made huge contributions to everyday lives. Machine learning provides more rational advice than humans are capable of in almost every aspect of daily life. However, despite this achievement, the design and training of neural networks are still challenging and unpredictable procedures. To lower the technical thresholds for common users, automated hyper-parameter optimization (HPO) has become a popular topic in both academic and industrial areas. This paper provides a review of the most essential topics on HPO. The first section introduces the key hyper-parameters related to model training and structure, and discusses their importance and methods to define the value range. Then, the research focuses on major optimization algorithms and their applicability, covering their efficiency and accuracy especially for deep learning networks. This study next reviews major services and toolkits for HPO, comparing their support for state-of-the-art searching algorithms, feasibility with major deep learning frameworks, and extensibility for new modules designed by users. The paper concludes with problems that exist when HPO is applied to deep learning, a comparison between optimization algorithms, and prominent approaches for model evaluation with limited computational resources.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191