United States

Model-based approaches to reinforcement learning (MBRL) exhibit favorable performance in practice, but their theoretical guarantees in large spaces are mostly restricted to the setting when the transition model is Gaussian or Lipschitz and demands a posterior estimate whose representational complexity grows unbounded with time. In this work, we develop a novel MBRL method (i) which relaxes the assumptions on the target transition model to belong to a generic family of mixture models; (ii) is applicable to large-scale training by incorporating a compression step such that the posterior estimate consists of a \emph{Bayesian coreset} of only statistically significant past state-action pairs; and (iii) {exhibits a Bayesian regret of $\mathcal{O}(dH^{1+({\alpha}/{2})}T^{1-({\alpha}/{2})})$ with coreset size of $\Omega(\sqrt{T^{1+\alpha}})$, where $d$ is the aggregate dimension of state action space, $H$ is the episode length, $T$ is the total number of time steps experienced, and $\alpha\in (0,1]$ is the tuning parameter which is a novel introduction into the analysis of MBRL in this work. We note that we match the best-known regret (which is $\mathcal{O}(dH^{3/2}T^{1/2})$) for $\alpha=1$ but allow for estimates to fit to a more general class of posterior distributions than the prior art.} To achieve these results, we adopt an approach based upon Stein&#39;s method, which, under a smoothness condition on the constructed posterior and target, allows distributional distance to be evaluated in closed form as the kernelized Stein discrepancy (KSD). The aforementioned compression step is then computed in terms of greedily retaining only those samples which are more than a certain KSD away from the previous model estimate. Experimentally, we observe that this approach is competitive with several state of the art RL methodologies, and can achieve up-to $50\%$ reduction in wall clock time in some continuous control environments.

AAAI 2023

Posterior Coreset Construction with Kernelized Stein Discrepancy for Model-Based Reinforcement Learning

kernelized stein discrepancy

posterior sampling

model-based reinforcement learning

bayesian reinforcement learning

compression

ICPR 2020 is the premier international conference on Pattern Recognition, gathering leading researchers from around the world to present their latest achievements in Pattern Analysis and Recognition, applied Artificial Intelligence and Machine Learning. The topic of the year is " Putting Artificial intelligence to work on Patterns". 
For the first time, ICPR has employed a two-round review process similar to journal submissions, with new papers allowed to be submitted in either the first or second round and papers submitted in the first round and not accepted allowed to be revised and re-submitted for second round review. 

In this edition of the **ICPR 2020** Conference, there are 1407 Oral/Poster presentations organized in five Tracks: 
- Artificial Intelligence, Machine Learning for Pattern Analysis; 
- Biometrics, Human Analysis and Behavior Understanding; Computer Vision, Robotics and Intelligent Systems; 
- Document and Media Analysis; and 
- Image and Signal Processing. 

The **ICPR 2020** Main Conference program also includes 7 Keynotes from prominent world-renowned scientists, 8 Tutorials, 28 Demos, 8 Challenges, 2 Panels, as well as an Industry/Sponsor Exhibition. In addition, 41 Workshops on a range of important current and emerging research topics complete the ICPR 2020 program. 


ICPR 2020

Model-based approaches to reinforcement learning (MBRL) exhibit favorable performance in practice, but their theoretical guarantees in large spaces are mostly restricted to the setting when the transition model is Gaussian or Lipschitz and demands a posterior estimate whose representational complexity grows unbounded with time. In this work, we develop a novel MBRL method (i) which relaxes the assumptions on the target transition model to belong to a generic family of mixture models; (ii) is applicable to large-scale training by incorporating a compression step such that the posterior estimate consists of a \emph{Bayesian coreset} of only statistically significant past state-action pairs; and (iii) {exhibits a Bayesian regret of $\mathcal{O}(dH^{1+({\alpha}/{2})}T^{1-({\alpha}/{2})})$ with coreset size of $\Omega(\sqrt{T^{1+\alpha}})$, where $d$ is the aggregate dimension of state action space, $H$ is the episode length, $T$ is the total number of time steps experienced, and $\alpha\in (0,1]$ is the tuning parameter which is a novel introduction into the analysis of MBRL in this work. We note that we match the best-known regret (which is $\mathcal{O}(dH^{3/2}T^{1/2})$) for $\alpha=1$ but allow for estimates to fit to a more general class of posterior distributions than the prior art.} To achieve these results, we adopt an approach based upon Stein's method, which, under a smoothness condition on the constructed posterior and target, allows distributional distance to be evaluated in closed form as the kernelized Stein discrepancy (KSD). The aforementioned compression step is then computed in terms of greedily retaining only those samples which are more than a certain KSD away from the previous model estimate. Experimentally, we observe that this approach is competitive with several state of the art RL methodologies, and can achieve up-to $50\%$ reduction in wall clock time in some continuous control environments.

poster

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/registration/).


The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines.

We consider a voting scenario in which the resource to be voted upon may consist of both indivisible and divisible goods. This generalizes both the well-studied model of multiwinner voting and the recently introduced model of cake sharing. Under approval votes, we propose two variants of the extended justified representation (EJR) notion from multiwinner voting, a stronger one called EJR for mixed goods (EJR-M) and a weaker one called EJR up to 1 (EJR-1). We extend three multiwinner voting rules to our setting—GreedyEJR, the method of equal shares (MES), and proportional approval voting (PAV)—and show that while all three generalizations satisfy EJR-1, only the first one provides EJR-M. In addition, we derive tight bounds on the proportionality degree implied by EJR-M and EJR-1, and investigate the proportionality degree of our proposed rules.

Approval-Based Voting with Mixed Goods

Unsupervised depth completion aims to recover dense depth from the sparse one without using the ground-truth annotation. Although depth measurement obtained from LiDAR is usually sparse, it contains valid and real distance information, i.e., scale-consistent absolute depth values. Meanwhile, scale-agnostic counterparts seek to estimate relative depth and have achieved impressive performance. To leverage both the inherent characteristics, we thus suggest to model scale-consistent depth upon unsupervised scale-agnostic frameworks. Specifically, we propose the decomposed scale-consistent learning (DSCL) strategy, which disintegrates the absolute depth into relative depth prediction and global scale estimation, contributing to individual learning benefits. But unfortunately, most existing unsupervised scale-agnostic frameworks heavily suffer from depth holes due to the extremely sparse depth input and weak supervisory signal. To tackle this issue, we introduce the global depth guidance (GDG) module, which attentively propagates dense depth reference into the sparse target via novel dense-to-sparse attention. Extensive experiments show the superiority of our method on outdoor KITTI, ranking 1st and outperforming the best KBNet more than 12% in RMSE. Additionally, our approach achieves state-of-the-art performance on indoor NYUv2 benchmark as well.

DesNet: Decomposed Scale-Consistent Network for Unsupervised Depth Completion

Recent years have witnessed the rapid progress of image captioning. However, the demands for large memory storage and heavy computational burden prevent these captioning models from being deployed on mobile devices. The main obstacles lie in the heavyweight visual feature extractors (i.e., object detectors) and complicated cross-modal fusion networks. To this end, we propose LightCap, a lightweight image captioner for resource-limited devices. The core design is built on the recent CLIP model for efficient image captioning. To be specific, on the one hand, we leverage the CLIP model to extract the compact grid features without relying on the time-consuming object detectors. On the other hand, we transfer the image-text retrieval design of CLIP to image captioning scenarios by devising a novel visual concept extractor and a cross-modal modulator. We further optimize the cross-modal fusion model and parallel prediction heads via sequential and ensemble distillations. With the carefully designed architecture, our model merely contains 40M parameters, saving the model size by more than 75% and the FLOPs by more than 98% in comparison with the current state-of-the-art methods. In spite of the low capacity, our model still exhibits state-of-the-art performance on prevalent datasets, e.g., 136.6 CIDEr on COCO Karpathy test split. Testing on the smartphone with only a single CPU, the proposed LightCap exhibits a fast inference speed of 188ms per image, which is ready for practical applications.

Efficient Image Captioning for Edge Devices

Stroke extraction of Chinese characters plays an important role in the field of character recognition and generation. The most existing character stroke extraction methods focus on image morphological features. These methods usually lead to errors of cross strokes extraction and stroke matching due to rarely using stroke semantics and prior information. In this paper, we propose a deep learning-based character stroke ex-traction method that takes semantic features and prior information of strokes into consideration. This method consists of three parts: image registration-based stroke registration that establishes the rough registration of the reference strokes and the target as prior information; image semantic segmentation-based stroke segmentation that preliminarily separates target strokes into seven categories; and high-precision extraction of single strokes. In the stroke registration, we propose a structure deformable image registration network to achieve structure-deformable transformation while maintaining the stable morphology of single strokes for character images with complex structures. In order to verify the effectiveness of the method, we construct two datasets respectively for calligra-phy characters and regular handwriting characters. The exper-imental results show that our method strongly outperforms the baselines.

Stroke Extraction of Chinese Character Based on Deep Structure Deformable Image Registration

We present a simple linear programming (LP) based method to learn compact and interpretable sets of rules encoding the facts in a knowledge graph (KG) and use these rules to solve the KG completion problem. Our LP model chooses a set of rules of bounded complexity from a list of candidate first-order logic rules and assigns weights to them. The complexity bound is enforced via explicit constraints. We combine simple rule generation heuristics with our rule selection LP to obtain predictions with accuracy comparable to state-of-the-art codes, even while generating much more compact rule sets. Furthermore, when we take as input rules generated by other codes, we often improve interpretability by reducing the number of chosen rules, while maintaining accuracy.

Rule Induction in Knowledge Graphs Using Linear Programming

Current work in named entity recognition (NER) uses either cross entropy (CE) or conditional random fields (CRF) as the objective/loss functions to optimize the underlying NER model. Both of these traditional objective functions for the NER problem generally produce adequate performance when the data distribution is balanced and there are sufficient annotated training examples. But since NER is inherently an imbalanced tagging problem, the model performance under the low-resource settings could suffer using these standard objective functions. Based on  recent advances in area under the ROC curve (AUC) maximization, we propose to optimize the NER model by maximizing the AUC score. We give evidence that by simply combining two binary-classifiers that maximize the AUC score, significant performance improvement over traditional loss functions is achieved under low-resource NER settings. We also conduct extensive experiments to demonstrate the advantages of our method under the low-resource and highly-imbalanced data distribution settings. To the best of our knowledge, this is the first work that brings AUC maximization to the NER setting. Furthermore, we show that our method is agnostic to different types of NER embeddings, models and domains. The code to replicate this work will be provided upon request.

AUC Maximization for Low-Resource Named Entity Recognition

Deep neural networks (DNNs) for supervised learning can be viewed as a pipeline of the feature extractor (i.e., last hidden layer) and a linear classifier (i.e., output layer) that are trained jointly with stochastic gradient descent (SGD) on the loss function (e.g., cross-entropy). In each epoch, the true gradient of the loss function is estimated using a mini-batch sampled from the training set and model parameters are then updated with the mini-batch gradients. Although the latter provides an unbiased estimation of the former, they are subject to substantial variances derived from the size and number of sampled mini-batches, leading to noisy and jumpy updates. To stabilize such undesirable variance in estimating the true gradients, we propose In-Training Representation Alignment (ITRA) that explicitly aligns feature distributions of two different mini-batches with a matching loss in the SGD training process. We also provide a rigorous analysis of the desirable effects of the matching loss on feature representation learning: (1) extracting compact feature representation; (2) reducing over-adaption on mini-batches via an adaptively weighting mechanism; and (3) accommodating to multi-modalities. Finally, we conduct large-scale experiments on both image and text classifications to demonstrate its superior performance to the strong baselines.

Learning Compact Features via In-Training Representation Alignment

Face image synthesis has progressed beyond the point at which humans can effectively distinguish authentic faces from synthetically-generated ones. Recently developed synthetic face image detectors boast ``better-than-human'' discriminative ability, especially those guided by human perceptual intelligence during the model's training process. In this paper, we investigate whether these human-guided synthetic face detectors can assist non-expert human operators in the task of synthetic image detection when compared to models trained without human-guidance. We conducted a large-scale experiment with more than 1,560 subjects classifying whether an image shows an authentic or synthetically-generated face, and annotating regions supporting their decisions. In total, 56,015 annotations across 3,780 unique face images were collected. All subjects first examined samples without any AI support, followed by samples given (a) the AI's decision (``synthetic'' or ``authentic''), (b) class activation maps illustrating where the model deems salient for its decision, 
or (c) both the AI's decision and AI's saliency map. Synthetic faces were generated with six modern Generative Adversarial Networks. Interesting observations from this experiment include: (1) models trained with human-guidance, which are also more accurate in our experiments, offer better support to human examination of face images when compared to models trained traditionally using cross-entropy loss, (2) binary decisions presented to humans results in their better performance than when saliency maps are presented, (3) understanding the AI's accuracy helps humans to increase trust in a given model and thus increase their overall accuracy. This work demonstrates that although humans supported by machines achieve better-than-random accuracy of synthetic face detection, the approaches of supplying humans with AI support and of building trust are key factors determining high effectiveness of the human-AI tandem.

The Value of AI Guidance in Human Examination of Synthetically-Generated Faces

Dynamical systems are general models of change or movement over time with a broad area of applicability to many branches of science, including computer science and AI. Dynamic topological logic (DTL) is a formal framework for symbolic reasoning about dynamical systems. DTL can express various liveness and reachability conditions on such systems, but has the drawback that the only known axiomatisation requires an extended language. In this paper, we consider dynamic topological logic restricted to the class of scattered spaces. Scattered spaces appear in the context of computational logic as they provide semantics for provability and enjoy definable fixed points. We exhibit the first sound and complete dynamic topological logic in the original language of DTL. In particular, we show that the version of DTL based on the class of scattered spaces is finitely axiomatisable, and that the natural axiomatisation is  sound and complete.

Untangled: A Complete Dynamic Topological Logic

In this paper, we study the \underline{R}obust \underline{o}ptimization for \underline{se}quence \underline{Net}worked \underline{s}ubmodular maximization (RoseNets) problem. We interweave the robust optimization  with the sequence networked submodular maximization. The elements are connected by a directed acyclic graph and the objective function is not submodular on the elements but on the edges in the graph. Under such networked submodular scenario, the impact of removing an element from a sequence depends both on its position in the sequence and in the network. This makes the existing robust algorithms inapplicable and calls for new robust algorithms. In this paper, we take the first step to study the RoseNets problem. We design a robust greedy algorithms, which is robust against the removal of an arbitrary subset of the selected elements. The approximation ratio of the algorithm depends both on the number of the removed elements and the network topology. We further conduct experiments on real applications of recommendation and link prediction. The experimental results demonstrate the effectiveness of the proposed algorithm.

Posterior Coreset Construction with Kernelized Stein Discrepancy for Model-Based Reinforcement Learning

Downloads

Next from AAAI 2023

Approval-Based Voting with Mixed Goods

Similar lecture

Compact CNN Structure Learning by Knowledge Distillation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES