This paper presents a new multi-layered algorithm for motion planning under motion and sensing uncertainties for Linear Temporal Logic specifications. We propose a technique to guide a sampling-based search tree in the combined task and belief space using trajectories from a simplified model of the system, to make the problem computationally tractable. Our method eliminates the need to construct fine and accurate finite abstractions. We prove correctness and probabilistic completeness of our algorithm, and illustrate the benefits of our approach on several case studies. Our results show that guidance with a simplified belief space model allows for significant speed-up in planning for complex specifications.

The Common Information (CI) approach provides a systematic way to transform a multi-agent stochastic control problem to a single-agent partially observed Markov decision problem (POMDP) called the coordinator's POMDP. However, such a POMDP can be hard to solve due to its extraordinarily large action space. We propose a new algorithm for multi-agent stochastic control problems, called coordinator's heuristic search value iteration (CHSVI), that combines the CI approach and point-based POMDP algorithms for large action spaces. We demonstrate the algorithm through optimally solving several benchmark problems.

Generative Adversarial Networks (GANs) have shown compelling results in various tasks and applications in recent years. However, mode collapse remains a critical problem in GANs. In this paper, we propose a novel training pipeline to address the mode collapse issue of GANs. Different from existing methods, we propose to generalize the discriminator as feature embedding and maximize the entropy of distributions in the embedding space learned by the discriminator. Specifically, two regularization terms, i.e., Deep Local Linear Embedding (DLLE) and Deep Isometric feature Mapping (DIsoMap), are designed to encourage the discriminator to learn the structural information embedded in the data, such that the embedding space learned by the discriminator can be well-formed. Based on the well-learned embedding space supported by the discriminator, a non-parametric entropy estimator is designed to efficiently maximize the entropy of embedding vectors, playing as an approximation of maximizing the entropy of the generated distribution. By improving the discriminator and maximizing the distance of the most similar samples in the embedding space, our pipeline effectively reduces the mode collapse without sacrificing the quality of generated samples. Extensive experimental results show the effectiveness of our method, which outperforms the GAN baseline, MaF-GAN on CelebA (9.13 vs. 12.43 in FID) and surpasses the recent state-of-the-art energy-based model on the ANIME-FACE dataset (2.80 vs. 2.26 in Inception score). The code is available at https://github.com/HaozheLiu-ST/MEE

We present a new data analysis perspective to determine variable importance regardless of the underlying learning task. Traditionally, variable selection is considered an important step in supervised learning for both classification and regression problems. The variable selection also becomes critical when costs associated with the data collection and storage are considerably high for cases like remote sensing. Therefore, we propose a new methodology to select important variables from the data by first creating dependency networks among all variables and then ranking them (i.e. nodes) by graph centrality measures. Selecting Top-$n$ variables according to preferred centrality measure will yield a strong candidate subset of variables for further learning tasks e.g. clustering. We present our tool as a Shiny app which is a user-friendly interface development environment. We also extend the user interface for two well-known unsupervised variable selection methods from literature for comparison reasons.

Bayesian causal structure learning aims to learn a posterior distribution over directed acyclic graphs (DAGs), and the mechanisms that define the relationship between parent and child variables. By taking a Bayesian approach, it is possible to reason about the uncertainty of the causal model. The notion of modelling the uncertainty over models is particularly crucial for causal structure learning since the model could be unidentifiable when given only a finite amount of observational data. In this paper, we introduce a novel method to jointly learn the structure and mechanisms of the causal model using Variational Bayes, which we call Variational Bayes-DAG-GFlowNet (VBG). We extend the method of Bayesian causal structure learning using GFlowNets to learn not only the posterior distribution over the structure, but also the parameters of a linear-Gaussian model. Our results on simulated data suggest that VBG is competitive against several baselines in modelling the posterior over DAGs and mechanisms, while offering several advantages over existing methods, including the guarantee to sample acyclic graphs, and the flexibility to generalize to non-linear causal mechanisms.

MLconf gathers machine learning & AI enthusiasts from a broad range of industries and academic backgrounds to share new tools, tricks, platforms, algorithms and methods with a broad audience of practitioners. Each presentation offers an educational component to be shared with the community, in which specific algorithms and techniques can be shared and new applications of such are inspired. Today, we are making a call for presentations for our MLconf San Francisco conference to be held on October 19, 2023 at the Hotel Nikko in SF. The conference will feature presentations from across the machine learning landscape. If you, your team, organization, or colleague has done something innovative related to ML algorithms, Tools and Platforms, or Building and Managing Teams to solve hard problems, let us help you share your story. In your abstract, we encourage you to mention where you feel your techniques will transfer over into other Machine Learning applications, showing where it's relevant to the MLconf audience. Prior submissions have included presentations related to: Algorithms that have graduated from an academic/theory state and have proven to be effective, robust and scalable in production within industry application; Machine Learning/AI examples of specific challenges faced within current industry and how teams have found success by applying new algorithms and techniques or by applying modifications to existing practices for optimal outcomes; New platforms, tools for machine learning; New business practices for managing and growing data science teams; and Expanding machine learning to new domains. Abstracts should be 150-500 words in length and should illustrate the level of technicality in the proposed presentation. At the time of the event, presentations will be generally limited to 25-30 minutes in length in order to allow you to provide depth while also allowing for presentations from colleagues and Q&A. Emphasis should be given to the technical challenges, benchmarks, innovations and motivation for the development of models, algorithms and statistical models to analyze and draw inferences from patterns in data. Your presentation should definitely not be a product or sales pitch. ABSTRACT DEADLINE: June 30, 2023 Topics we are looking for include but are not limited to: AI/ML Ops Natural Language Processing Deep Learning Reinforcement Learning Data Science for Social Good Kernel Methods Causality Embeddings Recommendation Systems Quantum Computing and AI/ML Chemistry & AI/ML Pandemic Data & ML Model Interpretability Fraud Detection DeepFake Detection Generative Teaching Networks Facial Recognition/Biometric Identification Genetics & ML Experimental Reproducibility Best Practices Model Uncertainty and Data Drift Generative Adversarial Networks Transfer Learning Adversarial Machine Learning IoT and edge computing applications Genetic Algorithms Tensor Algebra Probabilistic Programming and Logic Machine Learning for Music and Art Bayesian Methods Markov Logic Networks Synthetic Art, Biology Ethics in Machine Learning Data / Algorithm Ethics Sketching Randomized Algorithms AI Education Game Theory Diversity in AI Community Detection Time Series Image Analysis Structured Learning using Neural Networks Healthcare & ML (Clinical Decision Support Systems, Record Keeping, Medical Imaging, etc.) FinTech & ML (Algorithmic Trading, Predictive Analytics, Fraud Detection & Prevention, Payments, etc.) In the spirit of sharing knowledge, presentation slides are shared with attendees and photographs and/or video footage of presentations are shared as well.

Autonomous robots are required to reason about the behaviour of dynamic agents in their environment. The creation of models to describe these relationships is typically accomplished through the application of causal discovery techniques. However, as it stands observational causal discovery techniques struggle to adequately cope with conditions such as causal sparsity and non-stationarity typically seen during online usage in autonomous agent domains. Meanwhile, interventional techniques are not always feasible due to domain restrictions. In order to better explore the issues facing observational techniques and promote further discussion of these topics we carry out a benchmark across 10 contemporary observational temporal causal discovery methods in the domain of autonomous driving. By evaluating these methods upon causal scenes drawn from real world datasets in addition to those generated synthetically we highlight where improvements need to be made in order to facilitate the application of causal discovery techniques to the aforementioned use-cases. Finally, we discuss potential directions for future work that could help better tackle the difficulties currently experienced by state of the art techniques.

We study entropy-regularized constrained Markov decision processes (CMDPs) under the soft-max parameterization, in which an agent aims to maximize the entropy-regularized value function while satisfying constraints on the expected total utility. By leveraging the entropy regularization, our theoretical analysis shows that its Lagrangian dual function is smooth and the Lagrangian duality gap can be decomposed into the primal optimality gap and the constraint violation. Furthermore, we propose an accelerated dual-descent method for entropy-regularized CMDPs. We prove that our method achieves the global convergence rate $\widetilde{\mathcal{O}}(1/T)$ for both the optimality gap and the constraint violation for entropy-regularized CMDPs. A discussion about a linear convergence rate for CMDPs with a single constraint is also provided.

Interval Markov Decision Processes (IMDPs) are finite-state uncertain Markov models, where the transition probabilities belong to intervals. Recently, there has been a surge of research on employing IMDPs as abstractions of stochastic systems for control synthesis. However, due to the absence of algorithms for synthesis over IMDPs with continuous action-spaces, the action-space is assumed discrete a-priori, which is a restrictive assumption for many applications. Motivated by this, we introduce continuous-action IMDPs (caIMDPs), where the bounds on transition probabilities are functions of the action variables, and study value iteration for maximizing expected cumulative rewards. Specifically, we decompose the max-min problem associated to value iteration to $|\mathcal{Q}|$ max problems, where $|\mathcal{Q}|$ is the number of states of the caIMDP. Then, exploiting the simple form of these max problems, we identify cases where value iteration over caIMDPs can be solved efficiently (e.g., with linear or convex programming). We also gain other interesting insights: e.g., in certain cases where the action set $\mathcal{A}$ is a polytope, synthesis over a discrete-action IMDP, where the actions are the vertices of $\mathcal{A}$, is sufficient for optimality. We demonstrate our results on a numerical example. Finally, we include a short discussion on employing caIMDPs as abstractions for control synthesis.

Machine learning models are often misspecified in the likelihood, which leads to a lack of robustness in the predictions. In this paper, we introduce a framework for correcting likelihood misspecifications in several paradigm agnostic noisy prior models and test the model's ability to remove the misspecification. The "ABC-GAN" framework introduced is a novel generative modeling paradigm, which combines Generative Adversarial Networks (GANs) and Approximate Bayesian Computation (ABC). This new paradigm assists the existing GANs by incorporating any subjective knowledge available about the modeling process via ABC, as a regularizer, resulting in a partially interpretable model that operates well under low data regimes. At the same time, unlike any Bayesian analysis, the explicit knowledge need not be perfect, since the generator in the GAN can be made arbitrarily complex. ABC-GAN eliminates the need for summary statistics and distance metrics as the discriminator implicitly learns them and enables simultaneous specification of multiple generative models. The model misspecification is simulated in our experiments by introducing noise of various biases and variances. The correction term is learnt via the ABC-GAN, with skip connections, referred to as skipGAN. The strength of the skip connection indicates the amount of correction needed or how misspecified the prior model is. Based on a simple experimental setup, we show that the ABC-GAN models not only correct the misspecification of the prior, but also perform as well as or better than the respective priors under noisier conditions. In this proposal, we show that ABC-GANs get the best of both worlds.