arXiv subjects

Yuan Zhou

Publications and source records attributed to Yuan Zhou.

At least 235 records · Page 13Linked to original sources

arXiv2021

Adversarial Sample Enhanced Domain Adaptation: A Case Study on Predictive Modeling with Electronic Health Records

With the successful adoption of machine learning on electronic health records (EHRs), numerous computational models have been deployed to address a variety of clinical problems. However, due to the heterogeneity of EHRs, models trained on different patient groups suffer from poor generalizability. How to mitigate domain shifts between the source patient group where the model is built upon and the target one where the model will be deployed becomes a critical issue. In this paper, we propose a data augmentation method to facilitate domain adaptation, which leverages knowledge from the source patient group when training model on the target one. Specifically, adversarially generated samples are used during domain adaptation to fill the generalization gap between the two patient groups. The proposed method is evaluated by a case study on different predictive modeling tasks on MIMIC-III EHR dataset. Results confirm the effectiveness of our method and the generality on different tasks.

cs.LG↗

arXiv2021

On-chip integrated waveguide amplifiers on Erbium-doped thin film lithium niobate on insulator

We demonstrate on-chip light amplification with integrated optical waveguide fabricated on erbium-doped thin film lithium niobate on insulator (TFLNOI) using the photolithography assisted chemo-mechanical etching (PLACE) technique. A maximum internal net gain of 18 dB in the small-signal-gain regime is measured at the peak emission wavelength of 1530 nm for a waveguide length of 3.6 cm, indicating a differential gain per unit length of 5 dB/cm. This work paves the way to the monolithic integration of diverse active and passive photonic components on the TFLNOI platform.

physics.optics↗

arXiv2020

Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity

In this paper we consider the problem of learning an $ε$-optimal policy for a discounted Markov Decision Process (MDP). Given an MDP with $S$ states, $A$ actions, the discount factor $γ\in (0,1)$, and an approximation threshold $ε> 0$, we provide a model-free algorithm to learn an $ε$-optimal policy with sample complexity $\tilde{O}(\frac{SA\ln(1/p)}{ε^2(1-γ)^{5.5}})$ (where the notation $\tilde{O}(\cdot)$ hides poly-logarithmic factors of $S,A,1/(1-γ)$, and $1/ε$) and success probability $(1-p)$. For small enough $ε$, we show an improved algorithm with sample complexity $\tilde{O}(\frac{SA\ln(1/p)}{ε^2(1-γ)^{3}})$. While the first bound improves upon all known model-free algorithms and model-based ones with tight dependence on $S$, our second algorithm beats all known sample complexity bounds and matches the information theoretic lower bound up to logarithmic factors.

cs.LG↗

arXiv2020

Logic Synthesis Meets Machine Learning: Trading Exactness for Generalization

Logic synthesis is a fundamental step in hardware design whose goal is to find structural representations of Boolean functions while minimizing delay and area. If the function is completely-specified, the implementation accurately represents the function. If the function is incompletely-specified, the implementation has to be true only on the care set. While most of the algorithms in logic synthesis rely on SAT and Boolean methods to exactly implement the care set, we investigate learning in logic synthesis, attempting to trade exactness for generalization. This work is directly related to machine learning where the care set is the training set and the implementation is expected to generalize on a validation set. We present learning incompletely-specified functions based on the results of a competition conducted at IWLS 2020. The goal of the competition was to implement 100 functions given by a set of care minterms for training, while testing the implementation using a set of validation minterms sampled from the same function. We make this benchmark suite available and offer a detailed comparative analysis of the different approaches to learning

cs.LG↗

arXiv2020

Harnessing Distribution Ratio Estimators for Learning Agents with Quality and Diversity

Quality-Diversity (QD) is a concept from Neuroevolution with some intriguing applications to Reinforcement Learning. It facilitates learning a population of agents where each member is optimized to simultaneously accumulate high task-returns and exhibit behavioral diversity compared to other members. In this paper, we build on a recent kernel-based method for training a QD policy ensemble with Stein variational gradient descent. With kernels based on $f$-divergence between the stationary distributions of policies, we convert the problem to that of efficient estimation of the ratio of these stationary distributions. We then study various distribution ratio estimators used previously for off-policy evaluation and imitation and re-purpose them to compute the gradients for policies in an ensemble such that the resultant population is diverse and of high-quality.

cs.LG↗

arXiv2020

Multiple Dedekind Symbols

In this paper we study multiple Dedekind symbols and the associated multiple reciprocity functions. There is a bijection between the two sets of them after a normalization. By this bijection we define products of multiple reciprocity functions, and study the relationship to the shuffle property. We construct and calculate shuffled multiple Dedekind symbols and shuffled multiple reciprocity functions from modular forms by regularized iterated integrals. Also we give a decomposition for them.

math.NT↗

arXiv2020

Learning Guidance Rewards with Trajectory-space Smoothing

Long-term temporal credit assignment is an important challenge in deep reinforcement learning (RL). It refers to the ability of the agent to attribute actions to consequences that may occur after a long time interval. Existing policy-gradient and Q-learning algorithms typically rely on dense environmental rewards that provide rich short-term supervision and help with credit assignment. However, they struggle to solve tasks with delays between an action and the corresponding rewarding feedback. To make credit assignment easier, recent works have proposed algorithms to learn dense "guidance" rewards that could be used in place of the sparse or delayed environmental rewards. This paper is in the same vein -- starting with a surrogate RL objective that involves smoothing in the trajectory-space, we arrive at a new algorithm for learning guidance rewards. We show that the guidance rewards have an intuitive interpretation, and can be obtained without training any additional neural networks. Due to the ease of integration, we use the guidance rewards in a few popular algorithms (Q-learning, Actor-Critic, Distributional-RL) and present results in single-agent and multi-agent tasks that elucidate the benefit of our approach when the environmental rewards are sparse or delayed.

cs.LG↗

arXiv2020

Unsupervised Self-training Algorithm Based on Deep Learning for Optical Aerial Images Change Detection

Optical aerial images change detection is an important task in earth observation and has been extensively investigated in the past few decades. Generally, the supervised change detection methods with superior performance require a large amount of labeled training data which is obtained by manual annotation with high cost. In this paper, we present a novel unsupervised self-training algorithm (USTA) for optical aerial images change detection. The traditional method such as change vector analysis is used to generate the pseudo labels. We use these pseudo labels to train a well designed convolutional neural network. The network is used as a teacher to classify the original multitemporal images to generate another set of pseudo labels. Then two set of pseudo labels are used to jointly train a student network with the same structure as the teacher. The final change detection result can be obtained by the trained student network. Besides, we design an image filter to control the usage of change information in the pseudo labels in the training process of the network. The whole process of the algorithm is an unsupervised process without manually marked labels. Experimental results on the real datasets demonstrate competitive performance of our proposed method.

cs.CV↗

arXiv2020

Bayesian Policy Search for Stochastic Domains

AI planning can be cast as inference in probabilistic models, and probabilistic programming was shown to be capable of policy search in partially observable domains. Prior work introduces policy search through Markov chain Monte Carlo in deterministic domains, as well as adapts black-box variational inference to stochastic domains, however not in the strictly Bayesian sense. In this work, we cast policy search in stochastic domains as a Bayesian inference problem and provide a scheme for encoding such problems as nested probabilistic programs. We argue that probabilistic programs for policy search in stochastic domains should involve nested conditioning, and provide an adaption of Lightweight Metropolis-Hastings (LMH) for robust inference in such programs. We apply the proposed scheme to stochastic domains and show that policies of similar quality are learned, despite a simpler and more general inference algorithm. We believe that the proposed variant of LMH is novel and applicable to a wider class of probabilistic programs with nested conditioning.

cs.LG↗

arXiv2020

An on-chip tunable micro-disk laser fabricated on Er3+ doped lithium niobate on insulator (LNOI)

We demonstrate a C-band wavelength-tunable microlaser with an Er3+ doped high quality (~1.02x10^6) lithium niobate microdisk resonator. With a 976 nm continuous-wave pump laser, lasing action can be observed at a pump power threshold as low as ~250 μW at room temperature. Furthermore, the microdisk laser wavelength can be tuned by varying the pump laser power, showing a tuning efficiency of ~-17.03 pm/mW at low pump power blow 13 mW, and 10.58 pm/mW at high pump power above 13 mW.

physics.optics↗

arXiv2020

Enhancing spin-phonon and spin-spin interactions using linear resources in a hybrid quantum system

Hybrid spin-mechanical setups offer a versatile platform for quantum science and technology, but improving the spin-phonon as well as the spin-spin couplings of such systems remains a crucial challenge. Here, we propose and analyze an experimentally feasible and simple method for exponentially enhancing the spin-phonon, and the phonon-mediated spin-spin interactions in a hybrid spin-mechanical setup, using only \emph{ linear resources}. Through modulating the spring constant of the mechanical cantilever with a time-dependent pump, we can acquire a tunable and nonlinear (two-phonon) drive to the mechanical mode, thus amplifying the mechanical zero-point fluctuations and directly enhancing the spin-phonon coupling. Our method allows the spin-mechanical system to be driven from the weak-coupling regime to the strong-coupling regime, and even the ultrastrong coupling regime. In the dispersive regime, this method gives rise to a large enhancement of the phonon-mediated spin-spin interaction between distant solid-state spins, typically\emph{two orders of magnitude larger} than that without modulation. As an example, we show that the proposed scheme can apply to generating entangled states of multiple spins with high fidelities even in the presence of large dissipations.

quant-ph↗

arXiv2020

Efficient Competitive Self-Play Policy Optimization

Reinforcement learning from self-play has recently reported many successes. Self-play, where the agents compete with themselves, is often used to generate training data for iterative policy improvement. In previous work, heuristic rules are designed to choose an opponent for the current learner. Typical rules include choosing the latest agent, the best agent, or a random historical agent. However, these rules may be inefficient in practice and sometimes do not guarantee convergence even in the simplest matrix games. In this paper, we propose a new algorithmic framework for competitive self-play reinforcement learning in two-player zero-sum games. We recognize the fact that the Nash equilibrium coincides with the saddle point of the stochastic payoff function, which motivates us to borrow ideas from classical saddle point optimization literature. Our method trains several agents simultaneously, and intelligently takes each other as opponent based on simple adversarial rules derived from a principled perturbation-based saddle optimization method. We prove theoretically that our algorithm converges to an approximate equilibrium with high probability in convex-concave games under standard assumptions. Beyond the theory, we further show the empirical superiority of our method over baseline methods relying on the aforementioned opponent-selection heuristics in matrix games, grid-world soccer, Gomoku, and simulated robot sumo, with neural net policy function approximators.

cs.LG↗

arXiv2020

Collaborative Top Distribution Identifications with Limited Interaction

We consider the following problem in this paper: given a set of $n$ distributions, find the top-$m$ ones with the largest means. This problem is also called {\em top-$m$ arm identifications} in the literature of reinforcement learning, and has numerous applications. We study the problem in the collaborative learning model where we have multiple agents who can draw samples from the $n$ distributions in parallel. Our goal is to characterize the tradeoffs between the running time of learning process and the number of rounds of interaction between agents, which is very expensive in various scenarios. We give optimal time-round tradeoffs, as well as demonstrate complexity separations between top-$1$ arm identification and top-$m$ arm identifications for general $m$ and between fixed-time and fixed-confidence variants. As a byproduct, we also give an algorithm for selecting the distribution with the $m$-th largest mean in the collaborative learning model.

cs.DS↗

arXiv2020

Nearly Minimax-Optimal Regret for Linearly Parameterized Bandits

We study the linear contextual bandit problem with finite action sets. When the problem dimension is $d$, the time horizon is $T$, and there are $n \leq 2^{d/2}$ candidate actions per time period, we (1) show that the minimax expected regret is $Ω(\sqrt{dT (\log T) (\log n)})$ for every algorithm, and (2) introduce a Variable-Confidence-Level (VCL) SupLinUCB algorithm whose regret matches the lower bound up to iterated logarithmic factors. Our algorithmic result saves two $\sqrt{\log T}$ factors from previous analysis, and our information-theoretical lower bound also improves previous results by one $\sqrt{\log T}$ factor, revealing a regret scaling quite different from classical multi-armed bandits in which no logarithmic $T$ term is present in minimax regret. Our proof techniques include variable confidence levels and a careful analysis of layer sizes of SupLinUCB on the upper bound side, and delicately constructed adversarial sequences showing the tightness of elliptical potential lemmas on the lower bound side.

stat.ML↗

arXiv2020

Pooling Regularized Graph Neural Network for fMRI Biomarker Analysis

Understanding how certain brain regions relate to a specific neurological disorder has been an important area of neuroimaging research. A promising approach to identify the salient regions is using Graph Neural Networks (GNNs), which can be used to analyze graph structured data, e.g. brain networks constructed by functional magnetic resonance imaging (fMRI). We propose an interpretable GNN framework with a novel salient region selection mechanism to determine neurological brain biomarkers associated with disorders. Specifically, we design novel regularized pooling layers that highlight salient regions of interests (ROIs) so that we can infer which ROIs are important to identify a certain disease based on the node pooling scores calculated by the pooling layers. Our proposed framework, Pooling Regularized-GNN (PR-GNN), encourages reasonable ROI-selection and provides flexibility to preserve either individual- or group-level patterns. We apply the PR-GNN framework on a Biopoint Autism Spectral Disorder (ASD) fMRI dataset. We investigate different choices of the hyperparameters and show that PR-GNN outperforms baseline methods in terms of classification accuracy. The salient ROI detection results show high correspondence with the previous neuroimaging-derived biomarkers for ASD.

cs.CV↗

arXiv2020

Divide, Conquer, and Combine: a New Inference Strategy for Probabilistic Programs with Stochastic Support

Universal probabilistic programming systems (PPSs) provide a powerful framework for specifying rich probabilistic models. They further attempt to automate the process of drawing inferences from these models, but doing this successfully is severely hampered by the wide range of non--standard models they can express. As a result, although one can specify complex models in a universal PPS, the provided inference engines often fall far short of what is required. In particular, we show that they produce surprisingly unsatisfactory performance for models where the support varies between executions, often doing no better than importance sampling from the prior. To address this, we introduce a new inference framework: Divide, Conquer, and Combine, which remains efficient for such models, and show how it can be implemented as an automated and generic PPS inference engine. We empirically demonstrate substantial performance improvements over existing approaches on three examples.

stat.ML↗

arXiv2020

Multinomial Logit Bandit with Low Switching Cost

We study multinomial logit bandit with limited adaptivity, where the algorithms change their exploration actions as infrequently as possible when achieving almost optimal minimax regret. We propose two measures of adaptivity: the assortment switching cost and the more fine-grained item switching cost. We present an anytime algorithm (AT-DUCB) with $O(N \log T)$ assortment switches, almost matching the lower bound $Ω(\frac{N \log T}{ \log \log T})$. In the fixed-horizon setting, our algorithm FH-DUCB incurs $O(N \log \log T)$ assortment switches, matching the asymptotic lower bound. We also present the ESUCB algorithm with item switching cost $O(N \log^2 T)$.

cs.LG↗

arXiv2020

Giant anisotropy of spin relaxation and spin-valley mixing in a silicon quantum dot

In silicon quantum dots (QDs), at a certain magnetic field commonly referred to as the "hot spot", the electron spin relaxation rate (T_1^(-1)) can be drastically enhanced due to strong spin-valley mixing. Here, we experimentally find that with a valley splitting of 78.2 ${\pm}$ 1.6 $μ$eV, this hot spot in spin relaxation can be suppressed by more than 2 orders of magnitude when the in-plane magnetic field is oriented at an optimal angle, about 9° from the [100] sample plane. This directional anisotropy exhibits a sinusoidal modulation with a 180° periodicity. We explain the magnitude and phase of this modulation using a model that accounts for both spin-valley mixing and intravalley spin-orbit mixing. The generality of this phenomenon is also confirmed by tuning the electric field and the valley splitting up to 268.2 ${\pm}$ 0.7 $μ$eV.

cond-mat.mes-hall↗