arXiv subjects

Hao He

Publications and source records attributed to Hao He.

At least 127 records · Page 7Linked to original sources

arXiv2021

An Efficient Deep Distribution Network for Bid Shading in First-Price Auctions

Since 2019, most ad exchanges and sell-side platforms (SSPs), in the online advertising industry, shifted from second to first price auctions. Due to the fundamental difference between these auctions, demand-side platforms (DSPs) have had to update their bidding strategies to avoid bidding unnecessarily high and hence overpaying. Bid shading was proposed to adjust the bid price intended for second-price auctions, in order to balance cost and winning probability in a first-price auction setup. In this study, we introduce a novel deep distribution network for optimal bidding in both open (non-censored) and closed (censored) online first-price auctions. Offline and online A/B testing results show that our algorithm outperforms previous state-of-art algorithms in terms of both surplus and effective cost per action (eCPX) metrics. Furthermore, the algorithm is optimized in run-time and has been deployed into VerizonMedia DSP as production algorithm, serving hundreds of billions of bid requests per day. Online A/B test shows that advertiser's ROI are improved by +2.4%, +2.4%, and +8.6% for impression based (CPM), click based (CPC), and conversion based (CPA) campaigns respectively.

cs.GT↗

arXiv2021

Dependent Multi-Task Learning with Causal Intervention for Image Captioning

Recent work for image captioning mainly followed an extract-then-generate paradigm, pre-extracting a sequence of object-based features and then formulating image captioning as a single sequence-to-sequence task. Although promising, we observed two problems in generated captions: 1) content inconsistency where models would generate contradicting facts; 2) not informative enough where models would miss parts of important information. From a causal perspective, the reason is that models have captured spurious statistical correlations between visual features and certain expressions (e.g., visual features of "long hair" and "woman"). In this paper, we propose a dependent multi-task learning framework with the causal intervention (DMTCI). Firstly, we involve an intermediate task, bag-of-categories generation, before the final task, image captioning. The intermediate task would help the model better understand the visual features and thus alleviate the content inconsistency problem. Secondly, we apply Pearl's do-calculus on the model, cutting off the link between the visual features and possible confounders and thus letting models focus on the causal visual features. Specifically, the high-frequency concept set is considered as the proxy confounders where the real confounders are inferred in the continuous space. Finally, we use a multi-agent reinforcement learning (MARL) strategy to enable end-to-end training and reduce the inter-task error accumulations. The extensive experiments show that our model outperforms the baseline models and achieves competitive performance with state-of-the-art models.

cs.LG↗

arXiv2021

PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation

Aerial Image Segmentation is a particular semantic segmentation problem and has several challenging characteristics that general semantic segmentation does not have. There are two critical issues: The one is an extremely foreground-background imbalanced distribution, and the other is multiple small objects along with the complex background. Such problems make the recent dense affinity context modeling perform poorly even compared with baselines due to over-introduced background context. To handle these problems, we propose a point-wise affinity propagation module based on the Feature Pyramid Network (FPN) framework, named PointFlow. Rather than dense affinity learning, a sparse affinity map is generated upon selected points between the adjacent features, which reduces the noise introduced by the background while keeping efficiency. In particular, we design a dual point matcher to select points from the salient area and object boundaries, respectively. Experimental results on three different aerial segmentation datasets suggest that the proposed method is more effective and efficient than state-of-the-art general semantic segmentation methods. Especially, our methods achieve the best speed and accuracy trade-off on three aerial benchmarks. Further experiments on three general semantic segmentation datasets prove the generality of our method. Code will be provided in (https: //github.com/lxtGH/PFSegNets).

cs.CV↗

arXiv2020

Bid Shading by Win-Rate Estimation and Surplus Maximization

This paper describes a new win-rate based bid shading algorithm (WR) that does not rely on the minimum-bid-to-win feedback from a Sell-Side Platform (SSP). The method uses a modified logistic regression to predict the profit from each possible shaded bid price. The function form allows fast maximization at run-time, a key requirement for Real-Time Bidding (RTB) systems. We report production results from this method along with several other algorithms. We found that bid shading, in general, can deliver significant value to advertisers, reducing price per impression to about 55% of the unshaded cost. Further, the particular approach described in this paper captures 7% more profit for advertisers, than do benchmark methods of just bidding the most probable winning price. We also report 4.3% higher surplus than an industry Sell-Side Platform shading service. Furthermore, we observed 3% - 7% lower eCPM, eCPC and eCPA when the algorithm was integrated with budget controllers. We attribute the gains above as being mainly due to the explicit maximization of the surplus function, and note that other algorithms can take advantage of this same approach.

cs.GT↗

arXiv2020

Continuously Indexed Domain Adaptation

Existing domain adaptation focuses on transferring knowledge between domains with categorical indices (e.g., between datasets A and B). However, many tasks involve continuously indexed domains. For example, in medical applications, one often needs to transfer disease analysis and prediction across patients of different ages, where age acts as a continuous domain index. Such tasks are challenging for prior domain adaptation methods since they ignore the underlying relation among domains. In this paper, we propose the first method for continuously indexed domain adaptation. Our approach combines traditional adversarial adaptation with a novel discriminator that models the encoding-conditioned domain index distribution. Our theoretical analysis demonstrates the value of leveraging the domain index to generate invariant features across a continuous range of domains. Our empirical results show that our approach outperforms the state-of-the-art domain adaption methods on both synthetic and real-world medical datasets.

cs.LG↗

arXiv2020

Is this an Early Stage Merger? A Case Study on Molecular Gas and Star Formation Properties of Arp 240

We present new high resolution $^{12}$CO $J$=1-0, $J$=2-1, and $^{13}$CO $J$=1-0 maps of the early stage merger Arp 240 (NGC5257/8) obtained with the Atacama Large Millimeter/submillimeter Array (ALMA). Simulations in the literature suggest that the merger has just completed its first passage; however, we find that this system has a lower global gas fraction but a higher star formation efficiency compared to typical close galaxy pairs, which suggests that this system may already be in an advanced merger stage. We combine the ALMA data with $^{12}$CO $J$=3-2 observations from the Submillimeter Array and carry out RADEX modeling on several different regions. Both the RADEX modeling and a local thermal equilibrium (LTE) analysis show that the regions are most likely to have a CO-to-H$_2$ conversion factor $α_{\mathrm{CO}}$ close to or perhaps even smaller than the typical value for (ultra-)luminous infrared galaxies. Using 33 GHz data from the Very Large Array to measure the star formation rate, we find that most star forming regions have molecular gas depletion times of less than 100 Myr. We calculated the star formation efficiency (SFE) per free-fall time for different regions and find some regions appear to have values greater than 100%. We find these regions generally show evidence for young massive clusters (YMCs). After exploring various factors, we argue that this is mainly due to the fact that radio continuum emission in those regions is dominated by that from YMCs, which results in an overestimate of the SFE per free-fall time.

astro-ph.GA↗

arXiv2020

UST: Unifying Spatio-Temporal Context for Trajectory Prediction in Autonomous Driving

Trajectory prediction has always been a challenging problem for autonomous driving, since it needs to infer the latent intention from the behaviors and interactions from traffic participants. This problem is intrinsically hard, because each participant may behave differently under different environments and interactions. This key is to effectively model the interlaced influence from both spatial context and temporal context. Existing work usually encodes these two types of context separately, which would lead to inferior modeling of the scenarios. In this paper, we first propose a unified approach to treat time and space dimensions equally for modeling spatio-temporal context. The proposed module is simple and easy to implement within several lines of codes. In contrast to existing methods which heavily rely on recurrent neural network for temporal context and hand-crafted structure for spatial context, our method could automatically partition the spatio-temporal space to adapt the data. Lastly, we test our proposed framework on two recently proposed trajectory prediction dataset ApolloScape and Argoverse. We show that the proposed method substantially outperforms the previous state-of-the-art methods while maintaining its simplicity. These encouraging results further validate the superiority of our approach.

cs.CV↗

arXiv2020

Learning Compositional Koopman Operators for Model-Based Control

Finding an embedding space for a linear approximation of a nonlinear dynamical system enables efficient system identification and control synthesis. The Koopman operator theory lays the foundation for identifying the nonlinear-to-linear coordinate transformations with data-driven methods. Recently, researchers have proposed to use deep neural networks as a more expressive class of basis functions for calculating the Koopman operators. These approaches, however, assume a fixed dimensional state space; they are therefore not applicable to scenarios with a variable number of objects. In this paper, we propose to learn compositional Koopman operators, using graph neural networks to encode the state into object-centric embeddings and using a block-wise linear transition matrix to regularize the shared structure across objects. The learned dynamics can quickly adapt to new environments of unknown physical parameters and produce control signals to achieve a specified goal. Our experiments on manipulating ropes and controlling soft robots show that the proposed method has better efficiency and generalization ability than existing baselines.

cs.LG↗

arXiv2020

Truly Proximal Policy Optimization

Proximal policy optimization (PPO) is one of the most successful deep reinforcement-learning methods, achieving state-of-the-art performance across a wide range of challenging tasks. However, its optimization behavior is still far from being fully understood. In this paper, we show that PPO could neither strictly restrict the likelihood ratio as it attempts to do nor enforce a well-defined trust region constraint, which means that it may still suffer from the risk of performance instability. To address this issue, we present an enhanced PPO method, named Truly PPO. Two critical improvements are made in our method: 1) it adopts a new clipping function to support a rollback behavior to restrict the difference between the new policy and the old one; 2) the triggering condition for clipping is replaced with a trust region-based one, such that optimizing the resulted surrogate objective function provides guaranteed monotonic improvement of the ultimate policy performance. It seems, by adhering more truly to making the algorithm proximal - confining the policy within the trust region, the new algorithm improves the original PPO on both sample efficiency and performance.

cs.LG↗

arXiv2019

The CO(3-2)/CO(1-0) luminosity line ratio in nearby star-forming galaxies and AGN from xCOLD GASS, BASS and SLUGS

We study the r31=L'CO(3-2)/L'CO(1-0) luminosity line ratio in a sample of nearby (z < 0.05) galaxies: 25 star-forming galaxies (SFGs) from the xCOLD GASS survey, 36 hard X-ray selected AGN host galaxies from BASS and 37 infrared luminous galaxies from SLUGS. We find a trend for r31 to increase with star-formation efficiency (SFE). We model r31 using the UCL-PDR code and find that the gas density is the main parameter responsible for variation of r31, while the interstellar radiation field and cosmic ray ionization rate play only a minor role. We interpret these results to indicate a relation between SFE and gas density. We do not find a difference in the r31 value of SFGs and AGN host galaxies, when the galaxies are matched in SSFR ( = 0.52 +/- 0.04 for SFGs and = 0.53 +/- 0.06 for AGN hosts). According to the results of UCL-PDR models, the X-rays can contribute to the enhancement of the CO line ratio, but only for strong X-ray fluxes and for high gas density (nH > 10$^4$ cm-3). We find a mild tightening of the Kennicutt-Schmidt relation when we use the molecular gas mass surface density traced by CO(3-2) (Pearson correlation coefficient R=0.83), instead of the molecular gas mass surface density traced by CO(1-0) (R=0.78), but the increase in correlation is not statistically significant (p-value=0.06). This suggests that the CO(3-2) line can be reliably used to study the relation between SFR and molecular gas for normal SFGs at high redshift, and to compare it with studies of low-redshift galaxies, as is common practice.

astro-ph.GA↗

arXiv2019

Trust Region-Guided Proximal Policy Optimization

Proximal policy optimization (PPO) is one of the most popular deep reinforcement learning (RL) methods, achieving state-of-the-art performance across a wide range of challenging tasks. However, as a model-free RL method, the success of PPO relies heavily on the effectiveness of its exploratory policy search. In this paper, we give an in-depth analysis on the exploration behavior of PPO, and show that PPO is prone to suffer from the risk of lack of exploration especially under the case of bad initialization, which may lead to the failure of training or being trapped in bad local optima. To address these issues, we proposed a novel policy optimization method, named Trust Region-Guided PPO (TRGPPO), which adaptively adjusts the clipping range within the trust region. We formally show that this method not only improves the exploration ability within the trust region but enjoys a better performance bound compared to the original PPO as well. Extensive experiments verify the advantage of the proposed method.

cs.LG↗

arXiv2019

Disentangled Makeup Transfer with Generative Adversarial Network

Facial makeup transfer is a widely-used technology that aims to transfer the makeup style from a reference face image to a non-makeup face. Existing literature leverage the adversarial loss so that the generated faces are of high quality and realistic as real ones, but are only able to produce fixed outputs. Inspired by recent advances in disentangled representation, in this paper we propose DMT (Disentangled Makeup Transfer), a unified generative adversarial network to achieve different scenarios of makeup transfer. Our model contains an identity encoder as well as a makeup encoder to disentangle the personal identity and the makeup style for arbitrary face images. Based on the outputs of the two encoders, a decoder is employed to reconstruct the original faces. We also apply a discriminator to distinguish real faces from fake ones. As a result, our model can not only transfer the makeup styles from one or more reference face images to a non-makeup face with controllable strength, but also produce various outputs with styles sampled from a prior distribution. Extensive experiments demonstrate that our model is superior to existing literature by generating high-quality results for different scenarios of makeup transfer.

cs.CV↗

arXiv2019

Road-network-based Rapid Geolocalization

It has always been a research hotspot to use geographic information to assist the navigation of unmanned aerial vehicles. In this paper, a road-network-based localization method is proposed. We match roads in the measurement images to the reference road vector map, and realize successful localization on areas as large as a whole city. The road network matching problem is treated as a point cloud registration problem under two-dimensional projective transformation, and solved under a hypothesise-and-test framework. To deal with the projective point cloud registration problem, a global projective invariant feature is proposed, which consists of two road intersections augmented with the information of their tangents. We call it two road intersections tuple. We deduce the closed-form solution for determining the alignment transformation from a pair of matching two road intersections tuples. In addition, we propose the necessary conditions for the tuples to match. This can reduce the candidate matching tuples, thus accelerating the search to a great extent. We test all the candidate matching tuples under a hypothesise-and-test framework to search for the best match. The experiments show that our method can localize the target area over an area of 400 within 1 second on a single cpu.

cs.CV↗

arXiv2019

Robust Reinforcement Learning in POMDPs with Incomplete and Noisy Observations

In real-world scenarios, the observation data for reinforcement learning with continuous control is commonly noisy and part of it may be dynamically missing over time, which violates the assumption of many current methods developed for this. We addressed the issue within the framework of partially observable Markov Decision Process (POMDP) using a model-based method, in which the transition model is estimated from the incomplete and noisy observations using a newly proposed surrogate loss function with local approximation, while the policy and value function is learned with the help of belief imputation. For the latter purpose, a generative model is constructed and is seamlessly incorporated into the belief updating procedure of POMDP, which enables robust execution even under a significant incompleteness and noise. The effectiveness of the proposed method is verified on a collection of benchmark tasks, showing that our approach outperforms several compared methods under various challenging scenarios.

cs.LG↗

arXiv2019

Bidirectional Inference Networks: A Class of Deep Bayesian Networks for Health Profiling

We consider the problem of inferring the values of an arbitrary set of variables (e.g., risk of diseases) given other observed variables (e.g., symptoms and diagnosed diseases) and high-dimensional signals (e.g., MRI images or EEG). This is a common problem in healthcare since variables of interest often differ for different patients. Existing methods including Bayesian networks and structured prediction either do not incorporate high-dimensional signals or fail to model conditional dependencies among variables. To address these issues, we propose bidirectional inference networks (BIN), which stich together multiple probabilistic neural networks, each modeling a conditional dependency. Predictions are then made via iteratively updating variables using backpropagation (BP) to maximize corresponding posterior probability. Furthermore, we extend BIN to composite BIN (CBIN), which involves the iterative prediction process in the training stage and improves both accuracy and computational efficiency by adaptively smoothing the optimization landscape. Experiments on synthetic and real-world datasets (a sleep study and a dermatology dataset) show that CBIN is a single model that can achieve state-of-the-art performance and obtain better accuracy in most inference tasks than multiple models each specifically trained for a different task.

stat.ML↗

arXiv2018

Exposure: A White-Box Photo Post-Processing Framework

Retouching can significantly elevate the visual appeal of photos, but many casual photographers lack the expertise to do this well. To address this problem, previous works have proposed automatic retouching systems based on supervised learning from paired training images acquired before and after manual editing. As it is difficult for users to acquire paired images that reflect their retouching preferences, we present in this paper a deep learning approach that is instead trained on unpaired data, namely a set of photographs that exhibits a retouching style the user likes, which is much easier to collect. Our system is formulated using deep convolutional neural networks that learn to apply different retouching operations on an input image. Network training with respect to various types of edits is enabled by modeling these retouching operations in a unified manner as resolution-independent differentiable filters. To apply the filters in a proper sequence and with suitable parameters, we employ a deep reinforcement learning approach that learns to make decisions on what action to take next, given the current state of the image. In contrast to many deep learning systems, ours provides users with an understandable solution in the form of conventional retouching edits, rather than just a "black-box" result. Through quantitative comparisons and user studies, we show that this technique generates retouching results consistent with the provided photo set.

cs.GR↗

arXiv2017

From Bayesian Sparsity to Gated Recurrent Nets

The iterations of many first-order algorithms, when applied to minimizing common regularized regression functions, often resemble neural network layers with pre-specified weights. This observation has prompted the development of learning-based approaches that purport to replace these iterations with enhanced surrogates forged as DNN models from available training data. For example, important NP-hard sparse estimation problems have recently benefitted from this genre of upgrade, with simple feedforward or recurrent networks ousting proximal gradient-based iterations. Analogously, this paper demonstrates that more powerful Bayesian algorithms for promoting sparsity, which rely on complex multi-loop majorization-minimization techniques, mirror the structure of more sophisticated long short-term memory (LSTM) networks, or alternative gated feedback networks previously designed for sequence prediction. As part of this development, we examine the parallels between latent variable trajectories operating across multiple time-scales during optimization, and the activations within deep network structures designed to adaptively model such characteristic sequences. The resulting insights lead to a novel sparse estimation system that, when granted training data, can estimate optimal solutions efficiently in regimes where other algorithms fail, including practical direction-of-arrival (DOA) and 3D geometry recovery problems. The underlying principles we expose are also suggestive of a learning process for a richer class of multi-loop algorithms in other domains.

cs.LG↗

arXiv2016

Prior Distributions for Ranking Problems

The ranking problem is to order a collection of units by some unobserved parameter, based on observations from the associated distribution. This problem arises naturally in a number of contexts, such as business, where we may want to rank potential projects by profitability; or science, where we may want to rank variables potentially associated with some trait by the strength of the association. Most approaches to this problem are empirical Bayesian, where we use the data to estimate the hyperparameters of the prior distribution, then use that distribution to estimate the unobserved parameter values. There are a number of different approaches to this problem, based on different loss functions for mis-ranking units. However, little has been done on the choice of prior distribution. Typical approaches involve choosing a conjugate prior for convenience, and estimating the hyperparameters by MLE from the whole dataset. In this paper, we look in more detail at the effect of choice of prior distribution on Bayesian ranking. We focus on the use of posterior mean for ranking, but many of our conclusions should apply to other ranking criteria, and it is not too difficult to adapt our methods to other choices of prior distributions.

stat.ME↗