Wepropose anend-to-end machine learning based approach for topological ordering using an encoder-decoder framework. Our encoder is a novel attention based graph neural network architecture called Topoformer which uses different topological transforms of a DAG for message passing.

Wepropose anend-to-end machine learning based approach for topological ordering using an encoder-decoder framework. Our encoder is a novel attention based graph neural network architecture called Topoformer which uses different topological transforms of a DAG for message passing.

Imitation learning (IL) enables agents to mimic expert behaviors. Most previous IL techniques focus on precisely imitating one policy through mass demonstrations. However, in many applications, what humans require is the ability to perform various tasks directly through a few demonstrations of corresponding tasks, where the agent would meet many unexpected changes when deployed. In this scenario, the agent is expected to not only imitate the demonstration but also adapt to unforeseen environmental changes. This motivates us to propose a new topic called imitator learning (ItorL), which aims to derive an imitator module that can on-the-fly reconstruct the imitation policies based on very limited expert demonstrations for different unseen tasks, without any extra adjustment. In this work, we focus on imitator learning based on only one expert demonstration. To solve ItorL, we propose Demo-Attention Actor-Critic (DAAC), which integrates IL into a reinforcement-learning paradigm that can regularize policies' behaviors in unexpected situations. Besides, for autonomous imitation policy building, we design a demonstration-based attention architecture for imitator policy that can effectively output imitated actions by adaptively tracing the suitable states in demonstrations. We develop a new navigation benchmark and a robot environment for \topic~and show that DAAC~outperforms previous imitation methods \textit{with large margins} both on seen and unseen tasks.

The problem of inferring object shape from a single 2D image is underconstrained. Prior knowledge about what objects are plausible can help, but even given such prior knowledge there may still be uncertainty about the shapes of occluded parts of objects. Recently, conditional neural radiance field (NeRF) models have been developed that can learn to infer good point estimates of 3D models from single 2D images. The problem of inferring uncertainty estimates for these models has received less attention. In this work, we propose probabilistic NeRF (ProbNeRF), a model and inference strategy for learning probabilistic generative models of 3D objects' shapes and appearances, and for doing posterior inference to recover those properties from 2D images. ProbNeRF is trained as a variational autoencoder, but at test time we use Hamiltonian Monte Carlo (HMC) for inference. Given one or a few 2D images of an object (which may be partially occluded), ProbNeRF is able not only to accurately model the parts it sees, but also to propose realistic and diverse hypotheses about the parts it does not see. We show that key to the success of ProbNeRF are (i) a deterministic rendering scheme, (ii) an annealed-HMC strategy, (iii) a hypernetwork-based decoder architecture, and (iv) doing inference over a full set of NeRF weights, rather than just a low-dimensional code.

This paper presents an empirical performance analysis of three project scheduling algorithms dealing with maximizing projects' net present value with unrestricted resources. The selected algorithms, being the most recently cited in the literature, are: Recursive Search (RS), Steepest Ascent Approach (SAA) and Hybrid Search (HS). The main motivation for this research is the lack of knowledge about the computational complexities of the RS, SAA, and HS algorithms, since all studies to date show some gaps in the analysis. Furthermore, the empirical analysis performed to date does not consider the fact that one algorithm (HS) uses a dual search strategy, which markedly improved the algorithm's performance, while the others don't. In order to obtain a fair performance comparison, we implemented the dual search strategy into the other two algorithms (RS and SAA), and the new algorithms were called Recursive Search Forward-Backward (RSFB) and Steepest Ascent Approach Forward-Backward (SAAFB). The algorithms RSFB, SAAFB, and HS were submitted to a factorial experiment with three different project network sampling characteristics. The results were analyzed using the Generalized Linear Models (GLM) statistical modeling technique that showed: a) the general computational costs of RSFB, SAAFB, and HS; b) the costs of restarting the search in the spanning tree as part of the total cost of the algorithms; c) and statistically significant differences between the distributions of the algorithms' results.

Market manipulation is tackled through regulation in traditional markets because of its detrimental effect on market efficiency and many participating financial actors. The recent increase of private retail investors due to new low-fee platforms and new asset classes such as decentralised digital currencies has increased the number of vulnerable actors due to lack of institutional sophistication and strong regulation. This paper proposes a method to detect illicit activity and inform investors on spoofing attempts, a well-known market manipulation technique. Our framework is based on a highly extendable Gated Recurrent Unit (GRU) model and allows the inclusion of market variables that can explain spoofing and potentially other illicit activities. The model is tested on granular order book data, in one of the most unregulated markets prone to spoofing with a large number of non-institutional traders. The results show that the model is performing well in an early detection context, allowing the identification of spoofing attempts soon enough to allow investors to react. This is the first step to a fully comprehensive model that will protect investors in various unregulated trading environments and regulators to identify illicit activity.

We explore the effects of architecture and training objective choice on amortized posterior predictive inference in probabilistic conditional generative models. We aim this work to be a counterpoint to a recent trend in the literature that stresses achieving good samples when the amount of conditioning data is large. We instead focus our attention on the case where the amount of conditioning data is small. We highlight specific architecture and objective choices that we find lead to qualitative and quantitative improvement to posterior inference in this low data regime. Specifically we explore the effects of choices of pooling operator and variational family on posterior quality in neural processes. Superior posterior predictive samples drawn from our novel neural process architectures are demonstrated via image completion/in-painting experiments.

Neural Processes (NPs) (Garnelo et al 2018a;b) approach regression by learning to map a context set of observed input-output pairs to a distribution over regression functions. Each function models the distribution of the output given an input, conditioned on the context. NPs have the benefit of fitting observed data efficiently with linear complexity in the number of context input-output pairs, and can learn a wide family of conditional distributions; they learn predictive distributions conditioned on context sets of arbitrary size. Nonetheless, we show that NPs suffer a fundamental drawback of underfitting, giving inaccurate predictions at the inputs of the observed data they condition on. We address this issue by incorporating attention into NPs, allowing each input location to attend to the relevant context points for the prediction. We show that this greatly improves the accuracy of predictions, results in noticeably faster training, and expands the range of functions that can be modelled.