QAISG
QAISG
  • Видео 50
  • Просмотров 7 624
Barren plateaus are swamped with traps
Title: Barren plateaus are swamped with traps
Speaker: Nikita A. Nemkov from National University of Science and Technology “MISIS”
Abstract:
Two main challenges preventing efficient training of variational quantum algorithms and quantummachine learning models are local minima and barren plateaus. Typically, barren plateaus areassociated with deep circuits, while shallow circuits have been shown to suffer from suboptimallocal minima. We point out a simple mechanism that creates exponentially many poor local minimaspecifically in the barren plateau regime. These local minima are trivial solutions, optimizing onlya few terms in the loss function, leaving the rest on their barren plateaus. More ...
Просмотров: 32

Видео

Entanglement enabled advantage for learning a bosonic random displacement channel41:24Entanglement enabled advantage for learning a bosonic random displacement channel
Entanglement enabled advantage for learning a bosonic random displacement channel
Просмотров 152 часа назад
Title: Entanglement-enabled advantage for learning a bosonic random displacement channel Author: Changhun Oh from Korea Advanced Institute of Science and Technology Abstract: We show that quantum entanglement can provide an exponential advantage in learning properties of a bosonic continuous-variable (CV) system. The task we consider is estimating a probabilistic mixture of displacement operato...
Accuracy vs Memory Advantage in the Quantum Simulation of Stochastic Processes1:06:05Accuracy vs Memory Advantage in the Quantum Simulation of Stochastic Processes
Accuracy vs Memory Advantage in the Quantum Simulation of Stochastic Processes
Просмотров 6514 дней назад
Title: Accuracy vs Memory Advantage in the Quantum Simulation of Stochastic Processes Speaker: Leonardo Banchi from University of Florence and INFN Sezione di Firenze Abstract: Many inference scenarios rely on extracting relevant information from known data in order to makefuture predictions. When the underlying stochastic process satisfies certain assumptions, there is adirect mapping between ...
Dissipation as a resource for quantum reservoir computing46:11Dissipation as a resource for quantum reservoir computing
Dissipation as a resource for quantum reservoir computing
Просмотров 155Месяц назад
Title: Dissipation as a resource for quantum reservoir computing Speaker: Antonio Sannia from Campus Universitat de les Illes Balears Abstract: Dissipation induced by interactions with an external environment typically hinders the performance of quantum computation, but in some cases can be turned out as a useful resource. We show the potential enhancement induced by dissipation in the field of...
Noise induced shallow circuits and absence of barren plateaus1:10:29Noise induced shallow circuits and absence of barren plateaus
Noise induced shallow circuits and absence of barren plateaus
Просмотров 135Месяц назад
Title: Noise-induced shallow circuits and absence of barren plateaus Speaker: Antonio Anna Mele from Freie Universitat Berlin Abstract: Motivated by realistic hardware considerations of the pre-fault-tolerant era, we comprehensively study the impact of uncorrected noise on quantum circuits. We first show that any noise `truncates' most quantum circuits to effectively logarithmic depth, in the t...
Generative Quantum Machine Learning via Denoising Diffusion Probabilistic Models1:17:58Generative Quantum Machine Learning via Denoising Diffusion Probabilistic Models
Generative Quantum Machine Learning via Denoising Diffusion Probabilistic Models
Просмотров 262Месяц назад
Title: Generative Quantum Machine Learning via Denoising Diffusion Probabilistic Models Speaker: Bingzhi Zhang from University of Southern California Abstract: Deep generative models are key-enabling technology to computer vision, text generation, and large language models. Denoising diffusion probabilistic models (DDPMs) have recently gained much attention due to their ability to generate dive...
On fundamental aspects of quantum extreme learning machines1:00:23On fundamental aspects of quantum extreme learning machines
On fundamental aspects of quantum extreme learning machines
Просмотров 1602 месяца назад
Title: On fundamental aspects of quantum extreme learning machines Speaker: Weijie Xiong from EPFL, Switzerland Abstract: Quantum Extreme Learning Machines (QELMs) have emerged as a promising framework for quantum machine learning. Their appeal lies in the rich feature map induced by the dynamics of a quantum substrate - the quantum reservoir - and the efficient post-measurement training via li...
Does provable absence of barren plateaus imply classical simulability？1:17:25Does provable absence of barren plateaus imply classical simulability？
Does provable absence of barren plateaus imply classical simulability？
Просмотров 1572 месяца назад
Title: Does provable absence of barren plateaus imply classical simulability? Or, why we need to rethink variational quantum computing Speaker: Marco Cerezo from Los Alamos National Laboratory and Quantum Science Center, Oak Ridge Abstract: A large amount of effort has recently been put into understanding the barren plateau phenomenon. In this perspective article, we face the increasingly loud ...
Mapping out phase diagrams with generative classifiers50:28Mapping out phase diagrams with generative classifiers
Mapping out phase diagrams with generative classifiers
Просмотров 1103 месяца назад
Title: Mapping out phase diagrams with generative classifiers Speaker: Julian Arnold from University of Basel Abstract: One of the central tasks in many-body physics is the determination of phase diagrams. However, mapping out a phase diagram generally requires a great deal of human intuition and understanding. To automate this process, one can frame it as a classification task. Typically, clas...
Random Natural Gradient52:30Random Natural Gradient
Random Natural Gradient
Просмотров 1113 месяца назад
Title: Random Natural Gradient Speaker: Ioannis Kolotouros from University of Edinburgh Abstract: Hybrid quantum-classical algorithms appear to be the most promising approach for near-term quantum applications. An important bottleneck is the classical optimization loop, where the multiple local minima and the emergence of barren plateaux make these approaches less appealing. To improve the opti...
The discrete adiabatic quantum linear system solver has lower constant factors than the ra51:45The discrete adiabatic quantum linear system solver has lower constant factors than the ra
The discrete adiabatic quantum linear system solver has lower constant factors than the ra
Просмотров 1053 месяца назад
Title: The discrete adiabatic quantum linear system solver has lower constant factors than the randomized adiabatic solver Speaker: Pedro C. S. Costa from Macquarie University and Quantum for New South Wales Abstract: The solution of linear systems of equations is the basis of many other quantum algorithms, and recent results provided an algorithm with optimal scaling in both the condition numb...
From explainable NLP to quantum dynamics prediction1:03:34From explainable NLP to quantum dynamics prediction
From explainable NLP to quantum dynamics prediction
Просмотров 4384 месяца назад
Title: From explainable NLP to quantum dynamics prediction: A two-way synergy between many-body quantum physics and temporal machine learning models Speaker: Thiparat Chotibut from Chulalongkorn University Abstract: In this talk, we will discuss our recent work that highlights the fruitful interplay between many-body quantum physics and temporal machine learning models. The first part, "Quantum...
On the expressivity of embedding quantum kernels1:07:39On the expressivity of embedding quantum kernels
On the expressivity of embedding quantum kernels
Просмотров 1654 месяца назад
Title: On the expressivity of embedding quantum kernels Speaker: Elies Gil-Fuster from Freie Universitat Berlin and Fraunhofer Heinrich Hertz Institute Abstract: One of the most natural connections between quantum and classical machine learning has been established in the context of kernel methods. Kernel methods rely on kernels, which are inner products of feature vectors living in large featu...
Symmetry invariant quantum machine learning force fields53:49Symmetry invariant quantum machine learning force fields
Symmetry invariant quantum machine learning force fields
Просмотров 1834 месяца назад
Title: Symmetry-invariant quantum machine learning force fields Speaker: Isabel Nha Minh Le from IBM Quantum and RWTH Aachen University Abstract: Machine learning techniques are essential tools to compute efficient, yet accurate, force fields for atomistic simulations. This approach has recently been extended to incorporate quantum computational methods, making use of variational quantum learni...
Provable Advantage of Parameterized Quantum Circuit in Function Approximation1:11:24Provable Advantage of Parameterized Quantum Circuit in Function Approximation
Provable Advantage of Parameterized Quantum Circuit in Function Approximation
Просмотров 3394 месяца назад
Title: Provable Advantage of Parameterized Quantum Circuit in Function Approximation Speaker: Yu Zhan from Wuhan University and Centre for Quantum Technologies Abstract: Understanding the power of parameterized quantum circuits (PQCs) in accomplishing machine learning tasks is one of the most important questions in quantum machine learning. In this paper, we analyze the expressivity of PQCs thr...
Model Independent Learning of Quantum Phases of Matter with Quantum Convolutional Neural Networks1:00:57Model Independent Learning of Quantum Phases of Matter with Quantum Convolutional Neural Networks
Model Independent Learning of Quantum Phases of Matter with Quantum Convolutional Neural Networks
Просмотров 1705 месяцев назад
Model Independent Learning of Quantum Phases of Matter with Quantum Convolutional Neural Networks
Evaluating analytic gradients of pulse programs on quantum computers41:57Evaluating analytic gradients of pulse programs on quantum computers
Evaluating analytic gradients of pulse programs on quantum computers
Просмотров 1136 месяцев назад
Evaluating analytic gradients of pulse programs on quantum computers
Quantum Regularized Least Squares46:40Quantum Regularized Least Squares
Quantum Regularized Least Squares
Просмотров 227 месяцев назад
Quantum Regularized Least Squares
QRAM A Survey and Critique57:53QRAM A Survey and Critique
QRAM A Survey and Critique
Просмотров 2497 месяцев назад
QRAM A Survey and Critique
Post-variational quantum neural networks52:41Post-variational quantum neural networks
Post-variational quantum neural networks
Просмотров 1177 месяцев назад
Post-variational quantum neural networks
Phase transition in Random Circuit Sampling1:01:34Phase transition in Random Circuit Sampling
Phase transition in Random Circuit Sampling
Просмотров 687 месяцев назад
Phase transition in Random Circuit Sampling
Understanding quantum machine learning also requires rethinking generalization1:12:10Understanding quantum machine learning also requires rethinking generalization
Understanding quantum machine learning also requires rethinking generalization
Просмотров 2857 месяцев назад
Understanding quantum machine learning also requires rethinking generalization
Systems Architecture for Quantum Random Access Memory56:33Systems Architecture for Quantum Random Access Memory
Systems Architecture for Quantum Random Access Memory
Просмотров 2118 месяцев назад
Systems Architecture for Quantum Random Access Memory
Transition role of entangled data in quantum machine learning1:11:56Transition role of entangled data in quantum machine learning
Transition role of entangled data in quantum machine learning
Просмотров 368 месяцев назад
Transition role of entangled data in quantum machine learning
Classical Verification of Quantum Learning59:38Classical Verification of Quantum Learning
Classical Verification of Quantum Learning
Просмотров 1798 месяцев назад
Classical Verification of Quantum Learning
Trainability barriers and opportunities in quantum generative modeling57:48Trainability barriers and opportunities in quantum generative modeling
Trainability barriers and opportunities in quantum generative modeling
Просмотров 1398 месяцев назад
Trainability barriers and opportunities in quantum generative modeling
On quantum backpropagation, information reuse, and cheating measurement collapse48:30On quantum backpropagation, information reuse, and cheating measurement collapse
On quantum backpropagation, information reuse, and cheating measurement collapse
Просмотров 969 месяцев назад
On quantum backpropagation, information reuse, and cheating measurement collapse
Comparing Generalization of Quantum and Classical Generative Models towards Practical QA46:57Comparing Generalization of Quantum and Classical Generative Models towards Practical QA
Comparing Generalization of Quantum and Classical Generative Models towards Practical QA
Просмотров 659 месяцев назад
Comparing Generalization of Quantum and Classical Generative Models towards Practical QA
Towards Provably Efficient Quantum Algorithms for Large scale Machine learning Models1:18:05Towards Provably Efficient Quantum Algorithms for Large scale Machine learning Models
Towards Provably Efficient Quantum Algorithms for Large scale Machine learning Models
Просмотров 1869 месяцев назад
Towards Provably Efficient Quantum Algorithms for Large scale Machine learning Models
On the Role of Entanglement and Statistics in Learnining55:20On the Role of Entanglement and Statistics in Learnining
On the Role of Entanglement and Statistics in Learnining
Просмотров 5410 месяцев назад
On the Role of Entanglement and Statistics in Learnining

Комментарии