Search

Recent success in Deep Reinforcement Learning (DRL) methods has shown that policy optimization with respect to an off-policy distribution via importance sampling is effective for sample reuse. In this paper, we show that the use of importance sampling could introduce high variance in the objective estimate. Specifically, we show in a principled way that the variance of importance sampling estimate grows quadratically with importance ratios and the large ratios could consequently jeopardize the effectiveness of surrogate objective optimization. We then propose a technique called sample dropout to bound the estimation variance by dropping out samples when their ratio deviation is too high. We instantiate this sample dropout technique on representative policy optimization algorithms, including TRPO, PPO, and ESPO, and demonstrate that it consistently boosts the performance of those DRL algorithms on both continuous and discrete action controls, including MuJoCo, DMControl and Atari video games. Our code is open-sourced at \url{https://github.com/LinZichuan/sdpo.git}.

Deep optical optimization has recently emerged as a new paradigm for designing computational imaging systems using only the output image as the objective. However, it has been limited to either simple optical systems consisting of a single element such as a diffractive optical element (DOE) or metalens, or the fine-tuning of compound lenses from good initial designs. Here we present a DeepLens design method based on curriculum learning, which is able to learn optical designs of compound lenses ab initio from randomly initialized surfaces without human intervention, therefore overcoming the need for a good initial design. We demonstrate the effectiveness of our approach by fully automatically designing both classical imaging lenses and a large field-of-view extended depth-of-field computational lens in a cellphone-style form factor, with highly aspheric surfaces and a short back focal length., Comment: Automatically design computational lenses from scratch with differentiable ray tracing

We revisit the estimation bias in policy gradients for the discounted episodic Markov decision process (MDP) from Deep Reinforcement Learning (DRL) perspective. The objective is formulated theoretically as the expected returns discounted over the time horizon. One of the major policy gradient biases is the state distribution shift: the state distribution used to estimate the gradients differs from the theoretical formulation in that it does not take into account the discount factor. Existing discussion of the influence of this bias was limited to the tabular and softmax cases in the literature. Therefore, in this paper, we extend it to the DRL setting where the policy is parameterized and demonstrate how this bias can lead to suboptimal policies theoretically. We then discuss why the empirically inaccurate implementations with shifted state distribution can still be effective. We show that, despite such state distribution shift, the policy gradient estimation bias can be reduced in the following three ways: 1) a small learning rate; 2) an adaptive-learning-rate-based optimizer; and 3) KL regularization. Specifically, we show that a smaller learning rate, or, an adaptive learning rate, such as that used by Adam and RSMProp optimizers, makes the policy optimization robust to the bias. We further draw connections between optimizers and the optimization regularization to show that both the KL and the reverse KL regularization can significantly rectify this bias. Moreover, we provide extensive experiments on continuous control tasks to support our analysis. Our paper sheds light on how successful PG algorithms optimize policies in the DRL setting, and contributes insights into the practical issues in DRL., Comment: 12 pages, 9 figures

Whole-slide images (WSI) in computational pathology have high resolution with gigapixel size, but are generally with sparse regions of interest, which leads to weak diagnostic relevance and data inefficiency for each area in the slide. Most of the existing methods rely on a multiple instance learning framework that requires densely sampling local patches at high magnification. The limitation is evident in the application stage as the heavy computation for extracting patch-level features is inevitable. In this paper, we develop RLogist, a benchmarking deep reinforcement learning (DRL) method for fast observation strategy on WSIs. Imitating the diagnostic logic of human pathologists, our RL agent learns how to find regions of observation value and obtain representative features across multiple resolution levels, without having to analyze each part of the WSI at the high magnification. We benchmark our method on two whole-slide level classification tasks, including detection of metastases in WSIs of lymph node sections, and subtyping of lung cancer. Experimental results demonstrate that RLogist achieves competitive classification performance compared to typical multiple instance learning algorithms, while having a significantly short observation path. In addition, the observation path given by RLogist provides good decision-making interpretability, and its ability of reading path navigation can potentially be used by pathologists for educational/assistive purposes. Our code is available at: \url{https://github.com/tencent-ailab/RLogist}., Comment: accepted by AAAI 2023

While many systems have been developed to train Graph Neural Networks (GNNs), efficient model inference and evaluation remain to be addressed. For instance, using the widely adopted node-wise approach, model evaluation can account for up to 94% of the time in the end-to-end training process due to neighbor explosion, which means that a node accesses its multi-hop neighbors. On the other hand, layer-wise inference avoids the neighbor explosion problem by conducting inference layer by layer such that the nodes only need their one-hop neighbors in each layer. However, implementing layer-wise inference requires substantial engineering efforts because users need to manually decompose a GNN model into layers for computation and split workload into batches to fit into device memory. In this paper, we develop Deep Graph Inference (DGI) -- a system for easy and efficient GNN model inference, which automatically translates the training code of a GNN model for layer-wise execution. DGI is general for various GNN models and different kinds of inference requests, and supports out-of-core execution on large graphs that cannot fit in CPU memory. Experimental results show that DGI consistently outperforms layer-wise inference across different datasets and hardware settings, and the speedup can be over 1,000x., Comment: 10 pages, 10 figures

User engagement prediction plays a critical role for designing interaction strategies to grow user engagement and increase revenue in online social platforms. Through the in-depth analysis of the real-world data from the world's largest professional social platforms, i.e., LinkedIn, we find that users expose diverse engagement patterns, and a major reason for the differences in user engagement patterns is that users have different intents. That is, people have different intents when using LinkedIn, e.g., applying for jobs, building connections, or checking notifications, which shows quite different engagement patterns. Meanwhile, user intents and the corresponding engagement patterns may change over time. Although such pattern differences and dynamics are essential for user engagement prediction, differentiating user engagement patterns based on user dynamic intents for better user engagement forecasting has not received enough attention in previous works. In this paper, we proposed a Dynamic Intent Guided Meta Network (DIGMN), which can explicitly model user intent varying with time and perform differentiated user engagement forecasting. Specifically, we derive some interpretable basic user intents as prior knowledge from data mining and introduce prior intents in explicitly modeling dynamic user intent. Furthermore, based on the dynamic user intent representations, we propose a meta predictor to perform differentiated user engagement forecasting. Through a comprehensive evaluation on LinkedIn anonymous user data, our method outperforms state-of-the-art baselines significantly, i.e., 2.96% and 3.48% absolute error reduction, on coarse-grained and fine-grained user engagement prediction tasks, respectively, demonstrating the effectiveness of our method., Comment: 10 pages, Accepted by WSDM'23

Let $t \in \{2,8,10,12,14,16,18\}$ and $n=31s+t\geq 14$, $d_{a}(n,5)$ and $d_{l}(n,5)$ be distances of binary $[n,5]$ optimal linear codes and optimal linear complementary dual (LCD) codes, respectively. We show that an $[n,5,d_{a}(n,5)]$ optimal linear code is not an LCD code, there is an $[n,5,d_{l}(n,5)]=[n,5,d_{a}(n,5)-1]$ optimal LCD code if $t\neq 16$, and an optimal $[n,5,d_{l}(n,5)]$ optimal LCD code has $d_{l}(n,5)=16s+6=d_{a}(n,5)-2$ for $t=16$. Combined with known results on optimal LCD code, $d_{l}(n,5)$ of all $[n,5]$ LCD codes are completely determined., Comment: 15pages,7tables

We study the adaption of soft actor-critic (SAC) from continuous action space to discrete action space. We revisit vanilla SAC and provide an in-depth understanding of its Q value underestimation and performance instability issues when applied to discrete settings. We thereby propose entropy-penalty and double average Q-learning with Q-clip to address these issues. Extensive experiments on typical benchmarks with discrete action space, including Atari games and a large-scale MOBA game, show the efficacy of our proposed method. Our code is at:https://github.com/coldsummerday/Revisiting-Discrete-SAC.

This paper introduces Honor of Kings Arena, a reinforcement learning (RL) environment based on Honor of Kings, one of the world's most popular games at present. Compared to other environments studied in most previous work, ours presents new generalization challenges for competitive reinforcement learning. It is a multi-agent problem with one agent competing against its opponent; and it requires the generalization ability as it has diverse targets to control and diverse opponents to compete with. We describe the observation, action, and reward specifications for the Honor of Kings domain and provide an open-source Python-based interface for communicating with the game engine. We provide twenty target heroes with a variety of tasks in Honor of Kings Arena and present initial baseline results for RL-based methods with feasible computing resources. Finally, we showcase the generalization challenges imposed by Honor of Kings Arena and possible remedies to the challenges. All of the software, including the environment-class, are publicly available at https://github.com/tencent-ailab/hok_env . The documentation is available at https://aiarena.tencent.com/hok/doc/ ., Comment: Accepted by NeurIPS 2022

Graph Neural Networks (GNNs) are popular machine learning methods for modeling graph data. A lot of GNNs perform well on homophily graphs while having unsatisfactory performance on heterophily graphs. Recently, some researchers turn their attention to designing GNNs for heterophily graphs by adjusting the message passing mechanism or enlarging the receptive field of the message passing. Different from existing works that mitigate the issues of heterophily from model design perspective, we propose to study heterophily graphs from an orthogonal perspective by rewiring the graph structure to reduce heterophily and making the traditional GNNs perform better. Through comprehensive empirical studies and analysis, we verify the potential of the rewiring methods. To fully exploit its potential, we propose a method named Deep Heterophily Graph Rewiring (DHGR) to rewire graphs by adding homophilic edges and pruning heterophilic edges. The detailed way of rewiring is determined by comparing the similarity of label/feature-distribution of node neighbors. Besides, we design a scalable implementation for DHGR to guarantee high efficiency. DHRG can be easily used as a plug-in module, i.e., a graph pre-processing step, for any GNNs, including both GNN for homophily and heterophily, to boost their performance on the node classification task. To the best of our knowledge, it is the first work studying graph rewiring for heterophily graphs. Extensive experiments on 11 public graph datasets demonstrate the superiority of our proposed methods., Comment: 11 pages

A key challenge of continual reinforcement learning (CRL) in dynamic environments is to promptly adapt the RL agent's behavior as the environment changes over its lifetime, while minimizing the catastrophic forgetting of the learned information. To address this challenge, in this article, we propose DaCoRL, i.e., dynamics-adaptive continual RL. DaCoRL learns a context-conditioned policy using progressive contextualization, which incrementally clusters a stream of stationary tasks in the dynamic environment into a series of contexts and opts for an expandable multihead neural network to approximate the policy. Specifically, we define a set of tasks with similar dynamics as an environmental context and formalize context inference as a procedure of online Bayesian infinite Gaussian mixture clustering on environment features, resorting to online Bayesian inference to infer the posterior distribution over contexts. Under the assumption of a Chinese restaurant process prior, this technique can accurately classify the current task as a previously seen context or instantiate a new context as needed without relying on any external indicator to signal environmental changes in advance. Furthermore, we employ an expandable multihead neural network whose output layer is synchronously expanded with the newly instantiated context, and a knowledge distillation regularization term for retaining the performance on learned tasks. As a general framework that can be coupled with various deep RL algorithms, DaCoRL features consistent superiority over existing methods in terms of the stability, overall performance and generalization ability, as verified by extensive experiments on several robot navigation and MuJoCo locomotion tasks., Comment: Accepted by IEEE Transactions on Neural Networks and Learning Systems, 2023

Learning rate is one of the most important hyper-parameters that has a significant influence on neural network training. Learning rate schedules are widely used in real practice to adjust the learning rate according to pre-defined schedules for fast convergence and good generalization. However, existing learning rate schedules are all heuristic algorithms and lack theoretical support. Therefore, people usually choose the learning rate schedules through multiple ad-hoc trials, and the obtained learning rate schedules are sub-optimal. To boost the performance of the obtained sub-optimal learning rate schedule, we propose a generic learning rate schedule plugin, called LEArning Rate Perturbation (LEAP), which can be applied to various learning rate schedules to improve the model training by introducing a certain perturbation to the learning rate. We found that, with such a simple yet effective strategy, training processing exponentially favors flat minima rather than sharp minima with guaranteed convergence, which leads to better generalization ability. In addition, we conduct extensive experiments which show that training with LEAP can improve the performance of various deep learning models on diverse datasets using various learning rate schedules (including constant learning rate)., Comment: 7 pages, Accepted by CIKM'22

Graph Neural Networks (GNNs) have shown expressive performance on graph representation learning by aggregating information from neighbors. Recently, some studies have discussed the importance of modeling neighborhood distribution on the graph. However, most existing GNNs aggregate neighbors' features through single statistic (e.g., mean, max, sum), which loses the information related to neighbor's feature distribution and therefore degrades the model performance. In this paper, inspired by the method of moment in statistical theory, we propose to model neighbor's feature distribution with multi-order moments. We design a novel GNN model, namely Mix-Moment Graph Neural Network (MM-GNN), which includes a Multi-order Moment Embedding (MME) module and an Element-wise Attention-based Moment Adaptor module. MM-GNN first calculates the multi-order moments of the neighbors for each node as signatures, and then use an Element-wise Attention-based Moment Adaptor to assign larger weights to important moments for each node and update node representations. We conduct extensive experiments on 15 real-world graphs (including social networks, citation networks and web-page networks etc.) to evaluate our model, and the results demonstrate the superiority of MM-GNN over existing state-of-the-art models., Comment: accepted by WSDM2023

Generating agents that can achieve zero-shot coordination (ZSC) with unseen partners is a new challenge in cooperative multi-agent reinforcement learning (MARL). Recently, some studies have made progress in ZSC by exposing the agents to diverse partners during the training process. They usually involve self-play when training the partners, implicitly assuming that the tasks are homogeneous. However, many real-world tasks are heterogeneous, and hence previous methods may be inefficient. In this paper, we study the heterogeneous ZSC problem for the first time and propose a general method based on coevolution, which coevolves two populations of agents and partners through three sub-processes: pairing, updating and selection. Experimental results on various heterogeneous tasks highlight the necessity of considering the heterogeneous setting and demonstrate that our proposed method is a promising solution for heterogeneous ZSC tasks.

Ground-based high contrast imaging (HCI) and extreme adaptive optics (AO) technologies have advanced to the point of enabling direct detections of gas-giant exoplanets orbiting beyond the snow lines around nearby young star systems. However, leftover wavefront errors using current HCI and AO technologies, realized as "speckles" in the coronagraphic science image, still limit HCI instrument sensitivities to detecting and characterizing lower-mass, closer-in, and/or older/colder exoplanetary systems. Improving the performance of AO wavefront sensors (WFSs) and control techniques is critical to improving such HCI instrument sensitivity. Here we present three different ongoing wavefront sensing and control project developments on the Santa cruz Extreme AO Laboratory (SEAL) testbed: (1) "multi-WFS single congugate AO (SCAO)" using the Fast Atmospheric Self-coherent camera (SCC) Technique (FAST) and a Shack Hartmann WFS, (2) pupil chopping for focal plane wavefront sensing, first with an external amplitude modulator and then with the DM as a phase-only modulator, and (3) a laboratory demonstration of enhanced linearity with the non-modulated bright Pyramid WFS (PWFS) compared to the regular PWFS. All three topics share a common theme of multi-WFS SCAO and/or second stage AO, presenting opportunities and applications to further investigate these techniques in the future., Comment: submitted to SPIE Astronomical Telescopes and Instrumentation 2022, paper number 12185-89

Advanced exfoliation techniques are crucial for exploring the intrinsic properties and applications of 2D materials. Though the recently discovered Au-enhanced exfoliation technique provides an effective strategy for preparation of large-scale 2D crystals, the high cost of gold hinders this method from being widely adopted in industrial applications. In addition, direct Au contact could significantly quench photoluminescence (PL) emission in 2D semiconductors. It is therefore crucial to find alternative metals that can replace gold to achieve efficient exfoliation of 2D materials. Here, we present a one-step Ag-assisted method that can efficiently exfoliate many large-area 2D monolayers, where the yield ratio is comparable to Au-enhanced exfoliation method. Differing from Au film, however, the surface roughness of as-prepared Ag films on SiO2/Si substrate is much higher, which facilitates the generation of surface plasmons resulting from the nanostructures formed on the rough Ag surface. More interestingly, the strong coupling between 2D semiconductor crystals (e.g. MoS2, MoSe2) and Ag film leads to a unique PL enhancement that has not been observed in other mechanical exfoliation techniques, which can be mainly attributed to enhanced light-matter interaction as a result of extended propagation of surface plasmonic polariton (SPP). Our work provides a lower-cost and universal Ag-assisted exfoliation method, while at the same offering enhanced SPP-matter interactions.

Few-shot learning is a challenging task that requires language models to generalize from limited examples. Large language models like GPT-3 and PaLM have made impressive progress in this area, but they still face difficulties in reasoning tasks such as GSM8K, a benchmark for arithmetic problems. To improve their reasoning skills, previous work has proposed to guide the language model with prompts that elicit a series of reasoning steps before giving the final answer, achieving a significant improvement on GSM8K from 17.9% to 58.1% in problem-solving rate. In this paper, we present DIVERSE (Diverse Verifier on Reasoning Step), a novel approach that further enhances the reasoning capability of language models. DIVERSE has three main components: first, it generates diverse prompts to explore different reasoning paths for the same question; second, it uses a verifier to filter out incorrect answers based on a weighted voting scheme; and third, it verifies each reasoning step individually instead of the whole chain. We evaluate DIVERSE on the latest language model code-davinci-002 and show that it achieves new state-of-the-art results on six of eight reasoning benchmarks (e.g., GSM8K 74.4% to 83.2%).

Deep neural networks (DNNs) have shown promising results for acoustic echo cancellation (AEC). But the DNN-based AEC models let through all near-end speakers including the interfering speech. In light of recent studies on personalized speech enhancement, we investigate the feasibility of personalized acoustic echo cancellation (PAEC) in this paper for full-duplex communications, where background noise and interfering speakers may coexist with acoustic echoes. Specifically, we first propose a novel backbone neural network termed as gated temporal convolutional neural network (GTCNN) that outperforms state-of-the-art AEC models in performance. Speaker embeddings like d-vectors are further adopted as auxiliary information to guide the GTCNN to focus on the target speaker. A special case in PAEC is that speech snippets of both parties on the call are enrolled. Experimental results show that auxiliary information from either the near-end speaker or the far-end speaker can improve the DNN-based AEC performance. Nevertheless, there is still much room for improvement in the utilization of the finite-dimensional speaker embeddings., Comment: submitted to INTERSPEECH 22

It is critical for a keyword spotting model to have a small footprint as it typically runs on-device with low computational resources. However, maintaining the previous SOTA performance with reduced model size is challenging. In addition, a far-field and noisy environment with multiple signals interference aggravates the problem causing the accuracy to degrade significantly. In this paper, we present a multi-channel ConvMixer for speech command recognitions. The novel architecture introduces an additional audio channel mixing for channel audio interaction in a multi-channel audio setting to achieve better noise-robust features with more efficient computation. Besides, we proposed a centroid based awareness component to enhance the system by equipping it with additional spatial geometry information in the latent feature projection space. We evaluate our model using the new MISP challenge 2021 dataset. Our model achieves significant improvement against the official baseline with a 55% gain in the competition score (0.152) on raw microphone array input and a 63% (0.126) boost upon front-end speech enhancement., Comment: submitted to INTERSPEECH 2022

In this paper we propose a novel sparse optical flow (SOF)-based line feature tracking method for the camera pose estimation problem. This method is inspired by the point-based SOF algorithm and developed based on an observation that two adjacent images in time-varying image sequences satisfy brightness invariant. Based on this observation, we re-define the goal of line feature tracking: track two endpoints of a line feature instead of the entire line based on gray value matching instead of descriptor matching. To achieve this goal, an efficient two endpoint tracking (TET) method is presented: first, describe a given line feature with its two endpoints; next, track the two endpoints based on SOF to obtain two new tracked endpoints by minimizing a pixel-level grayscale residual function; finally, connect the two tracked endpoints to generate a new line feature. The correspondence is established between the given and the new line feature. Compared with current descriptor-based methods, our TET method needs not to compute descriptors and detect line features repeatedly. Naturally, it has an obvious advantage over computation. Experiments in several public benchmark datasets show our method yields highly competitive accuracy with an obvious advantage over speed.

The Transition Edge Sensor is extremely sensitive to the change of temperature, combined with the high-Z metal of a certain thickness, it can realize the high energy resolution measurement of particles such as X-rays. X-rays with energies below 10 keV have very weak penetrating ability, so only a few microns thick of gold or bismuth can obtain quantum efficiency higher than 70\%. Therefore, the entire structure of the TES X-ray detector in this energy range can be realized in the microfabrication process. However, for X-rays or gamma rays from 10 keV to 200 keV, sub-millimeter absorber layers are required, which cannot be realized by microfabrication process. This paper first briefly introduces a set of TES X-ray detectors and their auxiliary systems built by ShanghaiTech University, then focus on the introduction of the TES $\gamma$-ray detector, with absorber based on an sub-millimeter lead-tin alloy sphere. The detector has a quantum efficiency above 70\% near 100 keV, and an energy resolution of about 161.5eV@59.5keV., Comment: 13 pages, 12 figures

Recently the prompt-tuning paradigm has attracted significant attention. By only tuning continuous prompts with a frozen pre-trained language model (PLM), prompt-tuning takes a step towards deploying a shared frozen PLM to serve numerous downstream tasks. Although prompt-tuning shows good performance on certain natural language understanding (NLU) tasks, its effectiveness on natural language generation (NLG) tasks is still under-explored. In this paper, we argue that one of the factors hindering the development of prompt-tuning on NLG tasks is the unfamiliar inputs (i.e., inputs are linguistically different from the pretraining corpus). For example, our preliminary exploration reveals a large performance gap between prompt-tuning and fine-tuning when unfamiliar inputs occur frequently in NLG tasks. This motivates us to propose input-tuning, which fine-tunes both the continuous prompts and the input representations, leading to a more effective way to adapt unfamiliar inputs to frozen PLMs. Our proposed input-tuning is conceptually simple and empirically powerful. Experimental results on seven NLG tasks demonstrate that input-tuning is significantly and consistently better than prompt-tuning. Furthermore, on three of these tasks, input-tuning can achieve a comparable or even better performance than fine-tuning.