Predictive Probabilistic Merging of Policies (PPMP) google
Deep Reinforcement Learning has enabled the control of increasingly complex and high-dimensional problems. However, the need of vast amounts of data before reasonable performance is attained prevents its widespread application. We employ binary corrective feedback as a general and intuitive manner to incorporate human intuition and domain knowledge in model-free machine learning. The uncertainty in the policy and the corrective feedback is combined directly in the action space as probabilistic conditional exploration. As a result, the greatest part of the otherwise ignorant learning process can be avoided. We demonstrate the proposed method, Predictive Probabilistic Merging of Policies (PPMP), in combination with DDPG. In experiments on continuous control problems of the OpenAI Gym, we achieve drastic improvements in sample efficiency, final performance, and robustness to erroneous feedback, both for human and synthetic feedback. Additionally, we show solutions beyond the demonstrated knowledge. …

Deep Bayesian Multi-Target Learning (DBMTL) google
With the increasing variety of services that e-commerce platforms provide, criteria for evaluating their success become also increasingly multi-targeting. This work introduces a multi-target optimization framework with Bayesian modeling of the target events, called Deep Bayesian Multi-Target Learning (DBMTL). In this framework, target events are modeled as forming a Bayesian network, in which directed links are parameterized by hidden layers, and learned from training samples. The structure of Bayesian network is determined by model selection. We applied the framework to Taobao live-streaming recommendation, to simultaneously optimize (and strike a balance) on targets including click-through rate, user stay time in live room, purchasing behaviors and interactions. Significant improvement has been observed for the proposed method over other MTL frameworks and the non-MTL model. Our practice shows that with an integrated causality structure, we can effectively make the learning of a target benefit from other targets, creating significant synergy effects that improve all targets. The neural network construction guided by DBMTL fits in with the general probabilistic model connecting features and multiple targets, taking weaker assumption than the other methods discussed in this paper. This theoretical generality brings about practical generalization power over various targets distributions, including sparse targets and continuous-value ones. …

Delaunay Outlyingness google
Outlier detection is a major topic in robust statistics due to the high practical significance of anomalous observations. Many existing methods are, however, either parametric or cease to perform well when the data is far from linearly structured. In this paper, we propose a quantity, Delaunay outlyingness, that is a nonparametric outlyingness score applicable to data with complicated structure. The approach is based a well known triangulation of the sample, which seems to reflect the sparsity of the pointset to different directions in a useful way. In addition to appealing to heuristics, we derive results on the asymptotic behaviour of Delaunay outlyingness in the case of a sufficiently simple set of observations. Simulations and an application to financial data are also discussed. …

Semantic Adversarial Deep Learning google
Fueled by massive amounts of data, models produced by machine-learning (ML) algorithms, especially deep neural networks, are being used in diverse domains where trustworthiness is a concern, including automotive systems, finance, health care, natural language processing, and malware detection. Of particular concern is the use of ML algorithms in cyber-physical systems (CPS), such as self-driving cars and aviation, where an adversary can cause serious consequences. However, existing approaches to generating adversarial examples and devising robust ML algorithms mostly ignore the semantics and context of the overall system containing the ML component. For example, in an autonomous vehicle using deep learning for perception, not every adversarial example for the neural network might lead to a harmful consequence. Moreover, one may want to prioritize the search for adversarial examples towards those that significantly modify the desired semantics of the overall system. Along the same lines, existing algorithms for constructing robust ML algorithms ignore the specification of the overall system. In this paper, we argue that the semantics and specification of the overall system has a crucial role to play in this line of research. We present preliminary research results that support this claim. …

Advertisements