Abstract: Quantum compiling, a process that decomposes the quantum algorithm into a series of hardware-compatible commands or elementary gates, is of fundamental importance for quantum computing. We introduce an efficient algorithm based on deep reinforcement learning that compiles an arbitrary single-qubit gate into a sequence of elementary gates from a finite universal set. It generates near-optimal gate sequences with given accuracy and is generally applicable to various scenarios, independent of the hardware-feasible universal set and free from using ancillary qubits. For concreteness, we apply this algorithm to the case of topological compiling of Fibonacci anyons and obtain near-optimal braiding sequences for arbitrary single-qubit unitaries. Our algorithm may carry over to other challenging quantum discrete problems, thus opening up a new avenue for intriguing applications of deep learnin in quantum physics.

Abstract: Multi-task learning is a very challenging problem in reinforcement learning. While training multiple tasks jointly allow the policies to share parameters across different tasks, the optimization problem becomes non-trivial: It remains unclear what parameters in the network should be reused across tasks, and how the gradients from different tasks may interfere with each other. Thus, instead of naively sharing parameters across tasks, we introduce an explicit modularization technique on policy representation to alleviate this optimization issue. Given a base policy network, we design a routing network which estimates different routing strategies to reconfigure the base network for each task. Instead of directly selecting routes for each task, our task-specific policy uses a method called soft modularization to softly combine all the possible routes, which makes it suitable for sequential tasks. We experiment with various robotics manipulation tasks in simulation and show our method improves both sample efficiency and performance over strong baselines by a large margin. Our project page with code is at https://rchalyang.github.io/SoftModule/.

Abstract: We show that pre-trained Generative Adversarial Net-works (GANs), e.g., StyleGAN, can be used as a latent bank to improve the restoration quality of large-factor image super-resolution (SR). While most existing SR approaches attempt to generate realistic textures through learning with adversarial loss, our method, Generative LatEnt bANk (GLEAN), goes beyond existing practices by directly lever-aging rich and diverse priors encapsulated in a pre-trained GAN. But unlike prevalent GAN inversion methods that require expensive image-specific optimization at runtime, our approach only needs a single forward pass to generate the upscaled image. GLEAN can be easily incorporated in a simple encoder-bank-decoder architecture with multi-resolution skip connections. Switching the bank allows the method to deal with images from diverse categories, e.g.,cat, building, human face, and car. Images upscaled by GLEAN show clear improvements in terms of fidelity and texture faithfulness in comparison to existing methods as shown in Fig. 1.

Complex systems are the systems that consist of a great many diverse and autonomous but interacting and interdependent components whose aggregate behaviors are nonlinear. As phased by Aristotle, “the whole is more than the sum of its parts;” properties of complex systems are not a simple summation of their individual parts. Complex systems are widespread. Typical examples of complex systems can be found in the human brain, flocking formation of migrating birds, power grid, transportation systems, autonomous vehicles, social networks, and communication networks. Complex systems have some distinct properties, such as highly nonlinear dynamics, emergence, adaptation, and self-organization, which are difficult to model precisely. Such properties lead to difficulties in understanding the behaviors of complex systems, to model them accurately, to control them, and to make them work in a specific way we desire. There is no generally agreed definition of intelligent control. Generally speaking, intelligent control is a class of control methods that use artificial intelligence techniques, such as fuzzy logic, neural networks, evolutionary computation, machine learning,

Abstract:This paper investigates the robust cooperative output regulation problem of uncertain linear multi-agent systems with additive disturbances via the celebrated internal model principle. Two novel distributed controllers are designed based on the adaptive control strategy and the event-triggered transmission scheme, where the adaptive control strategy is utilized to avoid the requirement for a priori knowledge of the minimal nonzero eigenvalue of the Laplacian matrix associated with the communication topology, and the event-triggered transmission scheme is utilized to reduce the frequency of data transmission. It is shown that the proposed control schemes achieve robust cooperative output regulation asymptotically and Zeno behavior is excluded. Finally, a simulation example is presented to illustrate the effectiveness of the proposed controllers.

Abstract: Quantization has emerged as one of the most prevalent approaches to compress and accelerate neural networks. Recently, data-free quantization has been widely studied as a practical and promising solution. It synthesizes data for calibrating the quantized model according to the batch normalization (BN) statistics of FP32 ones and significantly relieves the heavy dependency on real training data in traditional quantization methods. Unfortunately, we find that in practice, the synthetic data identically constrained by BN statistics suffers serious homogenization at both distribution level and sample level and further causes a significant performance drop of the quantized model. We propose Diverse Sample Generation (DSG) scheme to mitigate the adverse effects caused by homogenization. Specifically, we slack the alignment of feature statistics in the BN layer to relax the constraint at the distribution level and design a layerwise enhancement to reinforce specific layers for different data samples. Our DSG scheme is versatile and even able to be applied to the state-of-the-art post-training quantization method like AdaRound. We evaluate the DSG scheme on the large-scale image classification task and consistently obtain significant improvements over various network architectures and quantization methods, especially when quantized to lower bits (e.g., up to 22% improvement on W4A4). Moreover, benefiting from the enhanced diversity, models calibrated with synthetic data perform close to those calibrated with real data and even outperform them on W4A4.