Throughout the course of my Ph.D., I have been designing the user experience (UX) of various machine learning (ML) systems. In this workshop, I share two projects as case studies in which people engage with ML in much more complicated and nuanced ways than the technical HCML work might assume. The first case study describes how cardiology teams in three hospitals used a clinical decision-support system that helps them decide whether and when to implant an artificial heart to a heart failure patient. I demonstrate that physicians cannot draw on their decision-making experience by seeing only patient data on paper. They are also confused by some fundamental premises upon which ML operates. For example, physicians asked: Are ML predictions made based on clinicians' best efforts? Is it ethical to make decisions based on previous patients' collective outcomes? In the second case study, my collaborators and I designed an intelligent text editor, with the goal of improving authors' writing experience with NLP (Natural Language Processing) technologies. We prototyped a number of generative functionalities where the system provides phrase-or-sentence-level writing suggestions upon user request. When writing with the prototype, however, authors shared that they need to "see where the sentence is going two paragraphs later" in order to decide whether the suggestion aligns with their writing; Some even considered adopting machine suggestions as plagiarism, therefore "is simply wrong". By sharing these unexpected and intriguing responses from these real-world ML users, I hope to start a discussion about such previously-unknown complexities and nuances of -- as the workshop proposal states -- "putting ML at the service of people in a way that is accessible, useful, and trustworthy to all".

While often stated as an instance of the likelihood ratio trick [Rubinstein, 1989], the original policy gradient theorem [Sutton, 1999] involves an integral over the action space. When this integral can be computed, the resulting "all-action" estimator [Sutton, 2001] provides a conditioning effect [Bratley, 1987] reducing the variance significantly compared to the REINFORCE estimator [Williams, 1992]. In this paper, we adopt a numerical integration perspective to broaden the applicability of the all-action estimator to general spaces and to any function class for the policy or critic components, beyond the Gaussian case considered by [Ciosek, 2018]. In addition, we provide a new theoretical result on the effect of using a biased critic which offers more guidance than the previous "compatible features" condition of [Sutton, 1999]. We demonstrate the benefit of our approach in continuous control tasks with nonlinear function approximation. Our results show improved performance and sample efficiency.

Existing approaches to amortized inference in probabilistic programs with unbounded loops can produce estimators with infinite variance. An instance of this is importance sampling inference in programs that explicitly include rejection sampling as part of the user-programmed generative procedure. In this paper we develop a new and efficient amortized importance sampling estimator. We prove finite variance of our estimator and empirically demonstrate our method's correctness and efficiency compared to existing alternatives on generative programs containing rejection sampling loops and discuss how to implement our method in a generic probabilistic programming framework.

Three variants of Kurt G\"odel's ontological argument, as proposed byDana Scott, C. Anthony Anderson and Melvin Fitting, are encoded and rigorously assessed on the computer. In contrast to Scott's version of G\"odel's argument, the two variants contributed by Anderson and Fitting avoid modal collapse. Although they appear quite different on a cursory reading, they are in fact closely related, as our computer-supported formal analysis (conducted in the proof assistant system Isabelle/HOL) reveals. Key to our formal analysis is the utilization of suitably adapted notions of (modal) ultrafilters, and a careful distinction between extensions and intensions of positive properties.

Industry has always been in the pursuit of becoming more economically efficient and the current focus has been to reduce human labour using modern technologies. Even with cutting edge technologies, which range from packaging robots to AI for fault detection, there is still some ambiguity on the aims of some new systems, namely, whether they are automated or autonomous. In this paper we indicate the distinctions between automated and autonomous system as well as review the current literature and identify the core challenges for creating learning mechanisms of autonomous agents. We discuss using different types of extended realities, such as digital twins, to train reinforcement learning agents to learn specific tasks through generalization. Once generalization is achieved, we discuss how these can be used to develop self-learning agents. We then introduce self-play scenarios and how they can be used to teach self-learning agents through a supportive environment which focuses on how the agents can adapt to different real-world environments.

Sequential decision making is a typical problem in reinforcement learning with plenty of algorithms to solve it. However, only a few of them can work effectively with a very small number of observations. In this report, we introduce the progress to learn the policy for Malaria Control as a Reinforcement Learning problem in the KDD Cup Challenge 2019 and propose diverse solutions to deal with the limited observations problem. We apply the Genetic Algorithm, Bayesian Optimization, Q-learning with sequence breaking to find the optimal policy for five years in a row with only 20 episodes/100 evaluations. We evaluate those algorithms and compare their performance with Random Search as a baseline. Among these algorithms, Q-Learning with sequence breaking has been submitted to the challenge and got ranked 7th in KDD Cup.

We present RLScheduler, a deep reinforcement learning based job scheduler for scheduling independent batch jobs in high-performance computing (HPC) environment. From knowing nothing about scheduling at beginning, RLScheduler is able to autonomously learn how to effectively schedule HPC batch jobs, targeting a given optimization goal. This is achieved by deep reinforcement learning with the help of specially designed neural network structures and various optimizations to stabilize and accelerate the learning. Our results show that RLScheduler can outperform existing heuristic scheduling algorithms, including a manually fine-tuned machine learning-based scheduler on the same workload. More importantly, we show that RLScheduler does not blindly over-fit the given workload to achieve such optimization, instead, it learns general rules for scheduling batch jobs which can be further applied to different workloads and systems to achieve similarly optimized performance. We also demonstrate that RLScheduler is capable of adjusting itself along with changing goals and workloads, making it an attractive solution for the future autonomous HPC management.

This paper describes a framework for the development of an integrative cognitive system based on probabilistic generative models (PGMs) called Neuro-SERKET. Neuro-SERKET is an extension of SERKET, which can compose elemental PGMs developed in a distributed manner and provide a scheme that allows the composed PGMs to learn throughout the system in an unsupervised way. In addition to the head-to-tail connection supported by SERKET, Neuro-SERKET supports tail-to-tail and head-to-head connections, as well as neural network-based modules, i.e., deep generative models. As an example of a Neuro-SERKET application, an integrative model was developed by composing a variational autoencoder (VAE), a Gaussian mixture model (GMM), latent Dirichlet allocation (LDA), and automatic speech recognition (ASR). The model is called VAE+GMM+LDA+ASR. The performance of VAE+GMM+LDA+ASR and the validity of Neuro-SERKET were demonstrated through a multimodal categorization task using image data and a speech signal of numerical digits.

This paper studies Learning from Observations (LfO) for imitation learning with access to state-only demonstrations. In contrast to Learning from Demonstration (LfD) that involves both action and state supervision, LfO is more practical in leveraging previously inapplicable resources (e.g. videos), yet more challenging due to the incomplete expert guidance. In this paper, we investigate LfO and its difference with LfD in both theoretical and practical perspectives. We first prove that the gap between LfD and LfO actually lies in the disagreement of inverse dynamics models between the imitator and the expert, if following the modeling approach of GAIL. More importantly, the upper bound of this gap is revealed by a negative causal entropy which can be minimized in a model-free way. We term our method as Inverse-Dynamics-Disagreement-Minimization (IDDM) which enhances the conventional LfO method through further bridging the gap to LfD. Considerable empirical results on challenging benchmarks indicate that our method attains consistent improvements over other LfO counterparts.

Several research groups worldwide are currently investigating how deep learning may advance the state-of-the-art in image and video coding. An open question is how to make deep neural networks work in conjunction with existing (and upcoming) video codecs, such as MPEG AVC/H.264, Such compatibility is a crucial aspect, as the video content industry and hardware manufacturers are expected to remain committed to supporting these standards for the foreseeable future. We propose deep neural networks as precoding components for current and future codec ecosystems. In our current deployments for DASH/HLS adaptive streaming, this comprises downscaling neural networks.