Paper Group ANR 166
Beyond Near- and Long-Term: Towards a Clearer Account of Research Priorities in AI Ethics and Society. Extended Stochastic Gradient MCMC for Large-Scale Bayesian Variable Selection. Learning Near Optimal Policies with Low Inherent Bellman Error. Monte Carlo Anti-Differentiation for Approximate Weighted Model Integration. Bridge the Domain Gap Betwe …
Beyond Near- and Long-Term: Towards a Clearer Account of Research Priorities in AI Ethics and Society
| Title | Beyond Near- and Long-Term: Towards a Clearer Account of Research Priorities in AI Ethics and Society |
| Authors | Carina Prunkl, Jess Whittlestone |
| Abstract | One way of carving up the broad “AI ethics and society” research space that has emerged in recent years is to distinguish between “near-term” and “long-term” research. While such ways of breaking down the research space can be useful, we put forward several concerns about the near/long-term distinction gaining too much prominence in how research questions and priorities are framed. We highlight some ambiguities and inconsistencies in how the distinction is used, and argue that while there are differing priorities within this broad research community, these differences are not well-captured by the near/long-term distinction. We unpack the near/long-term distinction into four different dimensions, and propose some ways that researchers can communicate more clearly about their work and priorities using these dimensions. We suggest that moving towards a more nuanced conversation about research priorities can help establish new opportunities for collaboration, aid the development of more consistent and coherent research agendas, and enable identification of previously neglected research areas. |
| Tasks | |
| Published | 2020-01-13 |
| URL | https://arxiv.org/abs/2001.04335v2 |
| https://arxiv.org/pdf/2001.04335v2.pdf | |
| PWC | https://paperswithcode.com/paper/beyond-near-and-long-term-towards-a-clearer |
| Repo | |
| Framework | |
Extended Stochastic Gradient MCMC for Large-Scale Bayesian Variable Selection
| Title | Extended Stochastic Gradient MCMC for Large-Scale Bayesian Variable Selection |
| Authors | Qifan Song, Yan Sun, Mao Ye, Faming Liang |
| Abstract | Stochastic gradient Markov chain Monte Carlo (MCMC) algorithms have received much attention in Bayesian computing for big data problems, but they are only applicable to a small class of problems for which the parameter space has a fixed dimension and the log-posterior density is differentiable with respect to the parameters. This paper proposes an extended stochastic gradient MCMC lgoriathm which, by introducing appropriate latent variables, can be applied to more general large-scale Bayesian computing problems, such as those involving dimension jumping and missing data. Numerical studies show that the proposed algorithm is highly scalable and much more efficient than traditional MCMC algorithms. The proposed algorithms have much alleviated the pain of Bayesian methods in big data computing. |
| Tasks | |
| Published | 2020-02-07 |
| URL | https://arxiv.org/abs/2002.02919v1 |
| https://arxiv.org/pdf/2002.02919v1.pdf | |
| PWC | https://paperswithcode.com/paper/extended-stochastic-gradient-mcmc-for-large |
| Repo | |
| Framework | |
Learning Near Optimal Policies with Low Inherent Bellman Error
| Title | Learning Near Optimal Policies with Low Inherent Bellman Error |
| Authors | Andrea Zanette, Alessandro Lazaric, Mykel Kochenderfer, Emma Brunskill |
| Abstract | We study the exploration problem with approximate linear action-value functions in episodic reinforcement learning under the notion of low inherent Bellman error, a condition normally employed to show convergence of approximate value iteration. First we relate this condition to other common frameworks and show that it is strictly more general than the low rank (or linear) MDP assumption of prior work. Second we provide an algorithm with a high probability regret bound $\widetilde O(\sum_{t=1}^H d_t \sqrt{K} + \sum_{t=1}^H \sqrt{d_t} \IBE K)$ where $H$ is the horizon, $K$ is the number of episodes, $\IBE$ is the value if the inherent Bellman error and $d_t$ is the feature dimension at timestep $t$. In addition, we show that the result is unimprovable beyond constants and logs by showing a matching lower bound. This has two important consequences: 1) the algorithm has the optimal statistical rate for this setting which is more general than prior work on low-rank MDPs 2) the lack of closedness (measured by the inherent Bellman error) is only amplified by $\sqrt{d_t}$ despite working in the online setting. Finally, the algorithm reduces to the celebrated \textsc{LinUCB} when $H=1$ but with a different choice of the exploration parameter that allows handling misspecified contextual linear bandits. While computational tractability questions remain open for the MDP setting, this enriches the class of MDPs with a linear representation for the action-value function where statistically efficient reinforcement learning is possible. |
| Tasks | |
| Published | 2020-02-29 |
| URL | https://arxiv.org/abs/2003.00153v2 |
| https://arxiv.org/pdf/2003.00153v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-near-optimal-policies-with-low |
| Repo | |
| Framework | |
Monte Carlo Anti-Differentiation for Approximate Weighted Model Integration
| Title | Monte Carlo Anti-Differentiation for Approximate Weighted Model Integration |
| Authors | Pedro Zuidberg Dos Martires, Samuel Kolb |
| Abstract | Probabilistic inference in the hybrid domain, i.e. inference over discrete-continuous domains, requires tackling two well known #P-hard problems 1)~weighted model counting (WMC) over discrete variables and 2)~integration over continuous variables. For both of these problems inference techniques have been developed separately in order to manage their #P-hardness, such as knowledge compilation for WMC and Monte Carlo (MC) methods for (approximate) integration in the continuous domain. Weighted model integration (WMI), the extension of WMC to the hybrid domain, has been proposed as a formalism to study probabilistic inference over discrete and continuous variables alike. Recently developed WMI solvers have focused on exploiting structure in WMI problems, for which they rely on symbolic integration to find the primitive of an integrand, i.e. to perform anti-differentiation. To combine these advances with state-of-the-art Monte Carlo integration techniques, we introduce \textit{Monte Carlo anti-differentiation} (MCAD), which computes MC approximations of anti-derivatives. In our empirical evaluation we substitute the exact symbolic integration backend in an existing WMI solver with an MCAD backend. Our experiments show that that equipping existing WMI solvers with MCAD yields a fast yet reliable approximate inference scheme. |
| Tasks | |
| Published | 2020-01-13 |
| URL | https://arxiv.org/abs/2001.04566v1 |
| https://arxiv.org/pdf/2001.04566v1.pdf | |
| PWC | https://paperswithcode.com/paper/monte-carlo-anti-differentiation-for |
| Repo | |
| Framework | |
Bridge the Domain Gap Between Ultra-wide-field and Traditional Fundus Images via Adversarial Domain Adaptation
| Title | Bridge the Domain Gap Between Ultra-wide-field and Traditional Fundus Images via Adversarial Domain Adaptation |
| Authors | Lie Ju, Xin Wang, Quan Zhou, Hu Zhu, Mehrtash Harandi, Paul Bonnington, Tom Drummond, Zongyuan Ge |
| Abstract | For decades, advances in retinal imaging technology have enabled effective diagnosis and management of retinal disease using fundus cameras. Recently, ultra-wide-field (UWF) fundus imaging by Optos camera is gradually put into use because of its broader insights on fundus for some lesions that are not typically seen in traditional fundus images. Research on traditional fundus images is an active topic but studies on UWF fundus images are few. One of the most important reasons is that UWF fundus images are hard to obtain. In this paper, for the first time, we explore domain adaptation from the traditional fundus to UWF fundus images. We propose a flexible framework to bridge the domain gap between two domains and co-train a UWF fundus diagnosis model by pseudo-labelling and adversarial learning. We design a regularisation technique to regulate the domain adaptation. Also, we apply MixUp to overcome the over-fitting issue from incorrect generated pseudo-labels. Our experimental results on either single or both domains demonstrate that the proposed method can well adapt and transfer the knowledge from traditional fundus images to UWF fundus images and improve the performance of retinal disease recognition. |
| Tasks | Domain Adaptation |
| Published | 2020-03-23 |
| URL | https://arxiv.org/abs/2003.10042v2 |
| https://arxiv.org/pdf/2003.10042v2.pdf | |
| PWC | https://paperswithcode.com/paper/bridge-the-domain-gap-between-ultra-wide |
| Repo | |
| Framework | |
Sharp Asymptotics and Optimal Performance for Inference in Binary Models
| Title | Sharp Asymptotics and Optimal Performance for Inference in Binary Models |
| Authors | Hossein Taheri, Ramtin Pedarsani, Christos Thrampoulidis |
| Abstract | We study convex empirical risk minimization for high-dimensional inference in binary models. Our first result sharply predicts the statistical performance of such estimators in the linear asymptotic regime under isotropic Gaussian features. Importantly, the predictions hold for a wide class of convex loss functions, which we exploit in order to prove a bound on the best achievable performance among them. Notably, we show that the proposed bound is tight for popular binary models (such as Signed, Logistic or Probit), by constructing appropriate loss functions that achieve it. More interestingly, for binary linear classification under the Logistic and Probit models, we prove that the performance of least-squares is no worse than 0.997 and 0.98 times the optimal one. Numerical simulations corroborate our theoretical findings and suggest they are accurate even for relatively small problem dimensions. |
| Tasks | |
| Published | 2020-02-17 |
| URL | https://arxiv.org/abs/2002.07284v2 |
| https://arxiv.org/pdf/2002.07284v2.pdf | |
| PWC | https://paperswithcode.com/paper/sharp-asymptotics-and-optimal-performance-for |
| Repo | |
| Framework | |
Bayesian Learning of Causal Relationships for System Reliability
| Title | Bayesian Learning of Causal Relationships for System Reliability |
| Authors | Xuewen Yu, Jim Q. Smith, Linda Nichols |
| Abstract | Causal theory is now widely developed with many applications to medicine and public health. However within the discipline of reliability, although causation is a key concept in this field, there has been much less theoretical attention. In this paper, we will demonstrate how some aspects of established causal methodology can be translated via trees, and more specifically chain event graphs, into domain of reliability theory to help the probability modeling of failures. We further show how various domain specific concepts of causality particular to reliability can be imported into more generic causal algebras and so demonstrate how these disciplines can inform each other. This paper is informed by a detailed analysis of maintenance records associated with a large electrical distribution company. Causal hypotheses embedded within these natural language texts are extracted and analyzed using the new graphical framework we introduced here. |
| Tasks | |
| Published | 2020-02-14 |
| URL | https://arxiv.org/abs/2002.06084v1 |
| https://arxiv.org/pdf/2002.06084v1.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-learning-of-causal-relationships-for |
| Repo | |
| Framework | |
Wasserstein-based Graph Alignment
| Title | Wasserstein-based Graph Alignment |
| Authors | Hermina Petric Maretic, Mireille El Gheche, Matthias Minder, Giovanni Chierchia, Pascal Frossard |
| Abstract | We propose a novel method for comparing non-aligned graphs of different sizes, based on the Wasserstein distance between graph signal distributions induced by the respective graph Laplacian matrices. Specifically, we cast a new formulation for the one-to-many graph alignment problem, which aims at matching a node in the smaller graph with one or more nodes in the larger graph. By integrating optimal transport in our graph comparison framework, we generate both a structurally-meaningful graph distance, and a signal transportation plan that models the structure of graph data. The resulting alignment problem is solved with stochastic gradient descent, where we use a novel Dykstra operator to ensure that the solution is a one-to-many (soft) assignment matrix. We demonstrate the performance of our novel framework on graph alignment and graph classification, and we show that our method leads to significant improvements with respect to the state-of-the-art algorithms for each of these tasks. |
| Tasks | Graph Classification |
| Published | 2020-03-12 |
| URL | https://arxiv.org/abs/2003.06048v1 |
| https://arxiv.org/pdf/2003.06048v1.pdf | |
| PWC | https://paperswithcode.com/paper/wasserstein-based-graph-alignment |
| Repo | |
| Framework | |
Distance Metric Learning for Graph Structured Data
| Title | Distance Metric Learning for Graph Structured Data |
| Authors | Tomoki Yoshida, Ichiro Takeuchi, Masayuki Karasuyama |
| Abstract | Graphs are versatile tools for representing structured data. Therefore, a variety of machine learning methods have been studied for graph data analysis. Although many of those learning methods depend on the measurement of differences between input graphs, defining an appropriate distance metric for a graph remains a controversial issue. Hence, we propose a supervised distance metric learning method for the graph classification problem. Our method, named interpretable graph metric learning (IGML), learns discriminative metrics in a subgraph-based feature space, which has a strong graph representation capability. By introducing a sparsity-inducing penalty on a weight of each subgraph, IGML can identify a small number of important subgraphs that can provide insight about the given classification task. Since our formulation has a large number of optimization variables, an efficient algorithm is also proposed by using pruning techniques based on safe screening and working set selection methods. An important property of IGML is that the optimality of the solution is guaranteed because the problem is formulated as a convex problem and our pruning strategies only discard unnecessary subgraphs. Further, we show that IGML is also applicable to other structured data such as item-set and sequence data, and that it can incorporate vertex-label similarity by using a transportation-based subgraph feature. We empirically evaluate the computational efficiency and classification performance on several benchmark datasets and show some illustrative examples demonstrating that IGML identifies important subgraphs from a given graph dataset. |
| Tasks | Graph Classification, Metric Learning |
| Published | 2020-02-03 |
| URL | https://arxiv.org/abs/2002.00727v1 |
| https://arxiv.org/pdf/2002.00727v1.pdf | |
| PWC | https://paperswithcode.com/paper/distance-metric-learning-for-graph-structured |
| Repo | |
| Framework | |
Clustering with Fast, Automated and Reproducible assessment applied to longitudinal neural tracking
| Title | Clustering with Fast, Automated and Reproducible assessment applied to longitudinal neural tracking |
| Authors | Hanlin Zhu, Xue Li, Liuyang Sun, Fei He, Zhengtuo Zhao, Lan Luan, Ngoc Mai Tran, Chong Xie |
| Abstract | Across many areas, from neural tracking to database entity resolution, manual assessment of clusters by human experts presents a bottleneck in rapid development of scalable and specialized clustering methods. To solve this problem we develop C-FAR, a novel method for Fast, Automated and Reproducible assessment of multiple hierarchical clustering algorithms simultaneously. Our algorithm takes any number of hierarchical clustering trees as input, then strategically queries pairs for human feedback, and outputs an optimal clustering among those nominated by these trees. While it is applicable to large dataset in any domain that utilizes pairwise comparisons for assessment, our flagship application is the cluster aggregation step in spike-sorting, the task of assigning waveforms (spikes) in recordings to neurons. On simulated data of 96 neurons under adverse conditions, including drifting and 25% blackout, our algorithm produces near-perfect tracking relative to the ground truth. Our runtime scales linearly in the number of input trees, making it a competitive computational tool. These results indicate that C-FAR is highly suitable as a model selection and assessment tool in clustering tasks. |
| Tasks | Entity Resolution, Model Selection |
| Published | 2020-03-19 |
| URL | https://arxiv.org/abs/2003.08533v1 |
| https://arxiv.org/pdf/2003.08533v1.pdf | |
| PWC | https://paperswithcode.com/paper/clustering-with-fast-automated-and |
| Repo | |
| Framework | |
Class-Specific Blind Deconvolutional Phase Retrieval Under a Generative Prior
| Title | Class-Specific Blind Deconvolutional Phase Retrieval Under a Generative Prior |
| Authors | Fahad Shamshad, Ali Ahmed |
| Abstract | In this paper, we consider the highly ill-posed problem of jointly recovering two real-valued signals from the phaseless measurements of their circular convolution. The problem arises in various imaging modalities such as Fourier ptychography, X-ray crystallography, and in visible light communication. We propose to solve this inverse problem using alternating gradient descent algorithm under two pretrained deep generative networks as priors; one is trained on sharp images and the other on blur kernels. The proposed recovery algorithm strives to find a sharp image and a blur kernel in the range of the respective pre-generators that \textit{best} explain the forward measurement model. In doing so, we are able to reconstruct quality image estimates. Moreover, the numerics show that the proposed approach performs well on the challenging measurement models that reflect the physically realizable imaging systems and is also robust to noise |
| Tasks | |
| Published | 2020-02-28 |
| URL | https://arxiv.org/abs/2002.12578v1 |
| https://arxiv.org/pdf/2002.12578v1.pdf | |
| PWC | https://paperswithcode.com/paper/class-specific-blind-deconvolutional-phase |
| Repo | |
| Framework | |
Learning Implicit Surface Light Fields
| Title | Learning Implicit Surface Light Fields |
| Authors | Michael Oechsle, Michael Niemeyer, Lars Mescheder, Thilo Strauss, Andreas Geiger |
| Abstract | Implicit representations of 3D objects have recently achieved impressive results on learning-based 3D reconstruction tasks. While existing works use simple texture models to represent object appearance, photo-realistic image synthesis requires reasoning about the complex interplay of light, geometry and surface properties. In this work, we propose a novel implicit representation for capturing the visual appearance of an object in terms of its surface light field. In contrast to existing representations, our implicit model represents surface light fields in a continuous fashion and independent of the geometry. Moreover, we condition the surface light field with respect to the location and color of a small light source. Compared to traditional surface light field models, this allows us to manipulate the light source and relight the object using environment maps. We further demonstrate the capabilities of our model to predict the visual appearance of an unseen object from a single real RGB image and corresponding 3D shape information. As evidenced by our experiments, our model is able to infer rich visual appearance including shadows and specular reflections. Finally, we show that the proposed representation can be embedded into a variational auto-encoder for generating novel appearances that conform to the specified illumination conditions. |
| Tasks | 3D Reconstruction, Image Generation |
| Published | 2020-03-27 |
| URL | https://arxiv.org/abs/2003.12406v1 |
| https://arxiv.org/pdf/2003.12406v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-implicit-surface-light-fields |
| Repo | |
| Framework | |
StrokeCoder: Path-Based Image Generation from Single Examples using Transformers
| Title | StrokeCoder: Path-Based Image Generation from Single Examples using Transformers |
| Authors | Sabine Wieluch, Friedhelm Schwenker |
| Abstract | This paper demonstrates how a Transformer Neural Network can be used to learn a Generative Model from a single path-based example image. We further show how a data set can be generated from the example image and how the model can be used to generate a large set of deviated images, which still represent the original image’s style and concept. |
| Tasks | Image Generation |
| Published | 2020-03-26 |
| URL | https://arxiv.org/abs/2003.11958v1 |
| https://arxiv.org/pdf/2003.11958v1.pdf | |
| PWC | https://paperswithcode.com/paper/strokecoder-path-based-image-generation-from |
| Repo | |
| Framework | |
Cycle Text-To-Image GAN with BERT
| Title | Cycle Text-To-Image GAN with BERT |
| Authors | Trevor Tsue, Samir Sen, Jason Li |
| Abstract | We explore novel approaches to the task of image generation from their respective captions, building on state-of-the-art GAN architectures. Particularly, we baseline our models with the Attention-based GANs that learn attention mappings from words to image features. To better capture the features of the descriptions, we then built a novel cyclic design that learns an inverse function to maps the image back to original caption. Additionally, we incorporated recently developed BERT pretrained word embeddings as our initial text featurizer and observe a noticeable improvement in qualitative and quantitative performance compared to the Attention GAN baseline. |
| Tasks | Image Generation, Word Embeddings |
| Published | 2020-03-26 |
| URL | https://arxiv.org/abs/2003.12137v1 |
| https://arxiv.org/pdf/2003.12137v1.pdf | |
| PWC | https://paperswithcode.com/paper/cycle-text-to-image-gan-with-bert |
| Repo | |
| Framework | |
Boolean learning under noise-perturbations in hardware neural networks
| Title | Boolean learning under noise-perturbations in hardware neural networks |
| Authors | Louis Andreoli, Xavier Porte, Stéphane Chrétien, Maxime Jacquot, Laurent Larger, Daniel Brunner |
| Abstract | A high efficiency hardware integration of neural networks benefits from realizing nonlinearity, network connectivity and learning fully in a physical substrate. Multiple systems have recently implemented some or all of these operations, yet the focus was placed on addressing technological challenges. Fundamental questions regarding learning in hardware neural networks remain largely unexplored. Noise in particular is unavoidable in such architectures, and here we investigate its interaction with a learning algorithm using an opto-electronic recurrent neural network. We find that noise strongly modifies the system’s path during convergence, and surprisingly fully decorrelates the final readout weight matrices. This highlights the importance of understanding architecture, noise and learning algorithm as interacting players, and therefore identifies the need for mathematical tools for noisy, analogue system optimization. |
| Tasks | |
| Published | 2020-03-27 |
| URL | https://arxiv.org/abs/2003.12319v1 |
| https://arxiv.org/pdf/2003.12319v1.pdf | |
| PWC | https://paperswithcode.com/paper/boolean-learning-under-noise-perturbations-in |
| Repo | |
| Framework | |
