Paper Group ANR 522
Model-free Feature Screening and FDR Control with Knockoff Features. Human vs. Muppet: A Conservative Estimate of Human Performance on the GLUE Benchmark. Combating the Compounding-Error Problem with a Multi-step Model. Augmented Random Search for Quadcopter Control: An alternative to Reinforcement Learning. Artificial Intelligence: A Child’s Play. …
Model-free Feature Screening and FDR Control with Knockoff Features
| Title | Model-free Feature Screening and FDR Control with Knockoff Features |
| Authors | Wanjun Liu, Yuan Ke, Runze Li |
| Abstract | This paper proposes a model-free and data-adaptive feature screening method for ultra-high dimensional datasets. The proposed method is based on the projection correlation which measures the dependence between two random vectors. This projection correlation based method does not require specifying a regression model and applies to the data in the presence of heavy-tailed errors and multivariate response. It enjoys both sure screening and rank consistency properties under weak assumptions. Further, a two-step approach is proposed to control the false discovery rate (FDR) in feature screening with the help of knockoff features. It can be shown that the proposed two-step approach enjoys both sure screening and FDR control if the pre-specified FDR level $\alpha$ is greater or equal to $1/s$, where $s$ is the number of active features. The superior empirical performance of the proposed methods is justified by various numerical experiments and real data applications. |
| Tasks | |
| Published | 2019-08-19 |
| URL | https://arxiv.org/abs/1908.06597v2 |
| https://arxiv.org/pdf/1908.06597v2.pdf | |
| PWC | https://paperswithcode.com/paper/model-free-feature-screening-with-projection |
| Repo | |
| Framework | |
Human vs. Muppet: A Conservative Estimate of Human Performance on the GLUE Benchmark
| Title | Human vs. Muppet: A Conservative Estimate of Human Performance on the GLUE Benchmark |
| Authors | Nikita Nangia, Samuel R. Bowman |
| Abstract | The GLUE benchmark (Wang et al., 2019b) is a suite of language understanding tasks which has seen dramatic progress in the past year, with average performance moving from 70.0 at launch to 83.9, state of the art at the time of writing (May 24, 2019). Here, we measure human performance on the benchmark, in order to learn whether significant headroom remains for further progress. We provide a conservative estimate of human performance on the benchmark through crowdsourcing: Our annotators are non-experts who must learn each task from a brief set of instructions and 20 examples. In spite of limited training, these annotators robustly outperform the state of the art on six of the nine GLUE tasks and achieve an average score of 87.1. Given the fast pace of progress however, the headroom we observe is quite limited. To reproduce the data-poor setting that our annotators must learn in, we also train the BERT model (Devlin et al., 2019) in limited-data regimes, and conclude that low-resource sentence classification remains a challenge for modern neural network approaches to text understanding. |
| Tasks | Sentence Classification |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10425v3 |
| https://arxiv.org/pdf/1905.10425v3.pdf | |
| PWC | https://paperswithcode.com/paper/human-vs-muppet-a-conservative-estimate-of |
| Repo | |
| Framework | |
Combating the Compounding-Error Problem with a Multi-step Model
| Title | Combating the Compounding-Error Problem with a Multi-step Model |
| Authors | Kavosh Asadi, Dipendra Misra, Seungchan Kim, Michel L. Littman |
| Abstract | Model-based reinforcement learning is an appealing framework for creating agents that learn, plan, and act in sequential environments. Model-based algorithms typically involve learning a transition model that takes a state and an action and outputs the next state—a one-step model. This model can be composed with itself to enable predicting multiple steps into the future, but one-step prediction errors can get magnified, leading to unacceptable inaccuracy. This compounding-error problem plagues planning and undermines model-based reinforcement learning. In this paper, we address the compounding-error problem by introducing a multi-step model that directly outputs the outcome of executing a sequence of actions. Novel theoretical and empirical results indicate that the multi-step model is more conducive to efficient value-function estimation, and it yields better action selection compared to the one-step model. These results make a strong case for using multi-step models in the context of model-based reinforcement learning. |
| Tasks | |
| Published | 2019-05-30 |
| URL | https://arxiv.org/abs/1905.13320v1 |
| https://arxiv.org/pdf/1905.13320v1.pdf | |
| PWC | https://paperswithcode.com/paper/combating-the-compounding-error-problem-with |
| Repo | |
| Framework | |
Augmented Random Search for Quadcopter Control: An alternative to Reinforcement Learning
| Title | Augmented Random Search for Quadcopter Control: An alternative to Reinforcement Learning |
| Authors | Ashutosh Kumar Tiwari, Sandeep Varma Nadimpalli |
| Abstract | Model-based reinforcement learning strategies are believed to exhibit more significant sample complexity than model-free strategies to control dynamical systems,such as quadcopters.This belief that Model-based strategies that involve the use of well-trained neural networks for making such high-level decisions always give better performance can be dispelled by making use of Model-free policy search methods.This paper proposes the use of a model-free random searching strategy,called Augmented Random Search(ARS),which is a better and faster approach of linear policy training for continuous control tasks like controlling a Quadcopters flight.The method achieves state-of-the-art accuracy by eliminating the use of too much data for the training of neural networks that are present in the previous approaches to the task of Quadcopter control.The paper also highlights the performance results of the searching strategy used for this task in a strategically designed task environment with the help of simulations.Reward collection performance over 1000 episodes and agents behavior in flight for augmented random search is compared with that of the behavior for reinforcement learning state-of-the-art algorithm,called Deep Deterministic policy gradient(DDPG).Our simulations and results manifest that a high variability in performance is observed in commonly used strategies for sample efficiency of such tasks but the built policy network of ARS-Quad can react relatively accurately to step response providing a better performing alternative to reinforcement learning strategies. |
| Tasks | Continuous Control |
| Published | 2019-11-28 |
| URL | https://arxiv.org/abs/1911.12553v1 |
| https://arxiv.org/pdf/1911.12553v1.pdf | |
| PWC | https://paperswithcode.com/paper/augmented-random-search-for-quadcopter |
| Repo | |
| Framework | |
Artificial Intelligence: A Child’s Play
| Title | Artificial Intelligence: A Child’s Play |
| Authors | Ravi Kashyap |
| Abstract | We discuss the objectives of any endeavor in creating artificial intelligence, AI, and provide a possible alternative. Intelligence might be an unintended consequence of curiosity left to roam free, best exemplified by a frolicking infant. This suggests that our attempts at AI could have been misguided; what we actually need to strive for can be termed artificial curiosity, AC, and intelligence happens as a consequence of those efforts. For this unintentional yet welcome aftereffect to set in a foundational list of guiding principles needs to be present. We discuss what these essential doctrines might be and why their establishment is required to form connections, possibly growing, between a knowledge store that has been built up and new pieces of information that curiosity will bring back. As more findings are acquired and more bonds are fermented, we need a way to, periodically, reduce the amount of data; in the sense, it is important to capture the critical characteristics of what has been accumulated or produce a summary of what has been gathered. We start with the intuition for this line of reasoning and formalize it with a series of models (and iterative improvements) that will be necessary to make the incubation of intelligence a reality. Our discussion provides conceptual modifications to the Turing Test and to Searle’s Chinese room argument. We discuss the future implications for society as AI becomes an integral part of life. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://arxiv.org/abs/1907.04659v1 |
| https://arxiv.org/pdf/1907.04659v1.pdf | |
| PWC | https://paperswithcode.com/paper/artificial-intelligence-a-childs-play |
| Repo | |
| Framework | |
Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference
| Title | Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference |
| Authors | Klas Leino, Matt Fredrikson |
| Abstract | Membership inference (MI) attacks exploit a learned model’s lack of generalization to infer whether a given sample was in the model’s training set. Known MI attacks generally work by casting the attacker’s goal as a supervised learning problem, training an attack model from predictions generated by the target model, or by others like it. However, we find that these attacks do not often provide a meaningful basis for confidently inferring training set membership, as the attack models are not well-calibrated. Moreover, these attacks do not significantly outperform a trivial attack that predicts that a point is a member if and only if the model correctly predicts its label. In this work we present well-calibrated MI attacks that allow the attacker to accurately control the minimum confidence with which positive membership inferences are made. Our attacks take advantage of white-box information about the target model and leverage new insights about how overfitting occurs in deep neural networks; namely, we show how a model’s idiosyncratic use of features can provide evidence for membership. Experiments on seven real-world datasets show that our attacks support calibration for high-confidence inferences, while outperforming previous MI attacks in terms of accuracy. Finally, we show that our attacks achieve non-trivial advantage on some models with low generalization error, including those trained with small-epsilon-differential privacy; for large-epsilon (epsilon=16, as reported in some industrial settings), the attack performs comparably to unprotected models. |
| Tasks | Calibration |
| Published | 2019-06-27 |
| URL | https://arxiv.org/abs/1906.11798v1 |
| https://arxiv.org/pdf/1906.11798v1.pdf | |
| PWC | https://paperswithcode.com/paper/stolen-memories-leveraging-model-memorization |
| Repo | |
| Framework | |
Forward and Backward Feature Selection for Query Performance Prediction
| Title | Forward and Backward Feature Selection for Query Performance Prediction |
| Authors | Sébastien Déjean, Radu Tudor Ionescu, Josiane Mothe, Md Zia Ullah |
| Abstract | The goal of query performance prediction (QPP) is to automatically estimate the effectiveness of a search result for any given query, without relevance judgements. Post-retrieval features have been shown to be more effective for this task while being more expensive to compute than pre-retrieval features. Combining multiple post-retrieval features is even more effective, but state-of-the-art QPP methods are impossible to interpret because of the black-box nature of the employed machine learning models. However, interpretation is useful for understanding the predictive model and providing more answers about its behavior. Moreover, combining many post-retrieval features is not applicable to real-world cases, since the query running time is of utter importance. In this paper, we investigate a new framework for feature selection in which the trained model explains well the prediction. We introduce a step-wise (forward and backward) model selection approach where different subsets of query features are used to fit different models from which the system selects the best one. We evaluate our approach on four TREC collections using standard QPP features. We also develop two QPP features to address the issue of query-drift in the query feedback setting. We found that: (1) our model based on a limited number of selected features is as good as more complex models for QPP and better than non-selective models; (2) our model is more efficient than complex models during inference time since it requires fewer features; (3) the predictive model is readable and understandable; and (4) one of our new QPP features is consistently selected across different collections, proving its usefulness. |
| Tasks | Feature Selection, Model Selection |
| Published | 2019-12-04 |
| URL | https://arxiv.org/abs/1912.04107v1 |
| https://arxiv.org/pdf/1912.04107v1.pdf | |
| PWC | https://paperswithcode.com/paper/forward-and-backward-feature-selection-for |
| Repo | |
| Framework | |
Deep Fundamental Factor Models
| Title | Deep Fundamental Factor Models |
| Authors | Matthew F. Dixon, Nicholas G. Polson |
| Abstract | Deep fundamental factor models are developed to interpret and capture non-linearity, interaction effects and non-parametric shocks in financial econometrics. Uncertainty quantification provides interpretability with interval estimation, ranking of factor importances and estimation of interaction effects. Estimating factor realizations under either homoscedastic or heteroscedastic error is also available. With no hidden layers we recover a linear factor model and for one or more hidden layers, uncertainty bands for the sensitivity to each input naturally arise from the network weights. To illustrate our methodology, we construct a six-factor model of assets in the S&P 500 index and generate information ratios that are three times greater than generalized linear regression. We show that the factor importances are materially different from the linear factor model when accounting for non-linearity. Finally, we conclude with directions for future research |
| Tasks | |
| Published | 2019-03-18 |
| URL | http://arxiv.org/abs/1903.07677v1 |
| http://arxiv.org/pdf/1903.07677v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-fundamental-factor-models |
| Repo | |
| Framework | |
Learning Clique Forests
| Title | Learning Clique Forests |
| Authors | Guido Previde Massara, Tomaso Aste |
| Abstract | We propose a topological learning algorithm for the estimation of the conditional dependency structure of large sets of random variables from sparse and noisy data. The algorithm, named Maximally Filtered Clique Forest (MFCF), produces a clique forest and an associated Markov Random Field (MRF) by generalising Prim’s minimum spanning tree algorithm. To the best of our knowledge, the MFCF presents three elements of novelty with respect to existing structure learning approaches. The first is the repeated application of a local topological move, the clique expansion, that preserves the decomposability of the underlying graph. Through this move the decomposability and calculation of scores is performed incrementally at the variable (rather than edge) level, and this provides better computational performance and an intuitive application of multivariate statistical tests. The second is the capability to accommodate a variety of score functions and, while this paper is focused on multivariate normal distributions, it can be directly generalised to different types of statistics. Finally, the third is the variable range of allowed clique sizes which is an adjustable topological constraint that acts as a topological penalizer providing a way to tackle sparsity at $l_0$ semi-norm level; this allows a clean decoupling of structure learning and parameter estimation. The MFCF produces a representation of the clique forest, together with a perfect ordering of the cliques and a perfect elimination ordering for the vertices. As an example we propose an application to covariance selection models and we show that the MCFC outperforms the Graphical Lasso for a number of classes of matrices. |
| Tasks | |
| Published | 2019-05-06 |
| URL | https://arxiv.org/abs/1905.02266v1 |
| https://arxiv.org/pdf/1905.02266v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-clique-forests |
| Repo | |
| Framework | |
Towards a Skeleton-Based Action Recognition For Realistic Scenarios
| Title | Towards a Skeleton-Based Action Recognition For Realistic Scenarios |
| Authors | Cagatay Odabasi, Jewel Jose |
| Abstract | Understanding human actions is a crucial problem for service robots. However, the general trend in Action Recognition is developing and testing these systems on structured datasets. That’s why this work presents a practical Skeleton-based Action Recognition framework which can be used in realistic scenarios. Our results show that although non-augmented and non-normalized data may yield comparable results on the test split of the dataset, it is far from being useful on another dataset which is a manually collected data. |
| Tasks | Skeleton Based Action Recognition, Temporal Action Localization |
| Published | 2019-05-14 |
| URL | https://arxiv.org/abs/1905.05420v1 |
| https://arxiv.org/pdf/1905.05420v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-a-skeleton-based-action-recognition |
| Repo | |
| Framework | |
Regret Bounds for Batched Bandits
| Title | Regret Bounds for Batched Bandits |
| Authors | Hossein Esfandiari, Amin Karbasi, Abbas Mehrabian, Vahab Mirrokni |
| Abstract | We present simple and efficient algorithms for the batched stochastic multi-armed bandit and batched stochastic linear bandit problems. We prove bounds for their expected regrets that improve over the best-known regret bounds for any number of batches. In particular, our algorithms in both settings achieve the optimal expected regrets by using only a logarithmic number of batches. We also study the batched adversarial multi-armed bandit problem for the first time and find the optimal regret, up to logarithmic factors, of any algorithm with predetermined batch sizes. |
| Tasks | Multi-Armed Bandits |
| Published | 2019-10-11 |
| URL | https://arxiv.org/abs/1910.04959v2 |
| https://arxiv.org/pdf/1910.04959v2.pdf | |
| PWC | https://paperswithcode.com/paper/batched-multi-armed-bandits-with-optimal |
| Repo | |
| Framework | |
Self-Supervised Fine-tuning for Image Enhancement of Super-Resolution Deep Neural Networks
| Title | Self-Supervised Fine-tuning for Image Enhancement of Super-Resolution Deep Neural Networks |
| Authors | Alice Lucas, Santiago Lopez-Tapia, Rafael Molina, Aggelos K. Katsaggelos |
| Abstract | While Deep Neural Networks (DNNs) trained for image and video super-resolution regularly achieve new state-of-the-art performance, they also suffer from significant drawbacks. One of their limitations is their tendency to generate strong artifacts in their solution. This may occur when the low-resolution image formation model does not match that seen during training. Artifacts also regularly arise when training Generative Adversarial Networks for inverse imaging problems. In this paper, we propose an efficient, fully self-supervised approach to remove the observed artifacts. More specifically, at test time, given an image and its known image formation model, we fine-tune the parameters of the trained network and iteratively update them using a data consistency loss. We apply our method to image and video super-resolution neural networks and show that our proposed framework consistently enhances the solution originally provided by the neural network. |
| Tasks | Image Enhancement, Super-Resolution, Video Super-Resolution |
| Published | 2019-12-30 |
| URL | https://arxiv.org/abs/1912.12879v1 |
| https://arxiv.org/pdf/1912.12879v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-supervised-fine-tuning-for-image |
| Repo | |
| Framework | |
Confluent-Drawing Parallel Coordinates: Web-Based Interactive Visual Analytics of Large Multi-Dimensional Data
| Title | Confluent-Drawing Parallel Coordinates: Web-Based Interactive Visual Analytics of Large Multi-Dimensional Data |
| Authors | Wenqiang Cui, Girts Strazdins, Hao Wang |
| Abstract | Parallel coordinates plot is one of the most popular and widely used visualization techniques for multi-dimensional data sets. Its main challenges for large-scale data sets are visual clutter and overplotting which hamper the recognition of patterns and trends in the data. In this paper, we propose a confluent drawing approach of parallel coordinates to support the web-based interactive visual analytics of large multi-dimensional data. The proposed method maps multi-dimensional data to node-link diagrams through the data binning-based clustering for each dimension. It uses density-based confluent drawing to visualize clusters and edges to reduce visual clutter and overplotting. Its rendering time is independent of the number of data items. It supports interactive visualization of large data sets without hardware acceleration in a normal web browser. Moreover, we design interactions to control the data binning process with this approach to support interactive visual analytics of large multi-dimensional data sets. Based on the proposed approach, we implement a web-based visual analytics application. The efficiency of the proposed method is examined through experiments on several data sets. The effectiveness of the proposed method is evaluated through a user study, in which two typical tasks of parallel coordinates plot are performed by participants to compare the proposed method with another parallel coordinates bundling technique. Results show that the proposed method significantly enhances the web-based interactive visual analytics of large multi-dimensional data. |
| Tasks | |
| Published | 2019-06-14 |
| URL | https://arxiv.org/abs/1906.10017v1 |
| https://arxiv.org/pdf/1906.10017v1.pdf | |
| PWC | https://paperswithcode.com/paper/confluent-drawing-parallel-coordinates-web |
| Repo | |
| Framework | |
Aplib: Tactical Programming of Intelligent Agents
| Title | Aplib: Tactical Programming of Intelligent Agents |
| Authors | I. S. W. B. Prasetya |
| Abstract | This paper presents aplib, a Java library for programming intelligent agents, featuring BDI and multi agency, but adding on top of it a novel layer of tactical programming inspired by the domain of theorem proving. Aplib is also implemented in such a way to provide the fluency of a Domain Specific Language (DSL). Compared to dedicated BDI agent programming languages such as JASON, 2APL, or GOAL,aplib’s embedded DSL approach does mean that \aplib\ programmers will still be limited by Java syntax, but on other hand they get all the advantages that Java programmers get: rich language features (object orientation, static type checking, $\lambda$-expression, libraries, etc), a whole array of development tools, integration with other technologies, large community, etc. |
| Tasks | Automated Theorem Proving |
| Published | 2019-11-12 |
| URL | https://arxiv.org/abs/1911.04710v1 |
| https://arxiv.org/pdf/1911.04710v1.pdf | |
| PWC | https://paperswithcode.com/paper/aplib-tactical-programming-of-intelligent |
| Repo | |
| Framework | |
Whole slide image registration for the study of tumor heterogeneity
| Title | Whole slide image registration for the study of tumor heterogeneity |
| Authors | Leslie Solorzano, Gabriela M. Almeida, Bárbara Mesquita, Diana Martins, Carla Oliveira, Carolina Wählby |
| Abstract | Consecutive thin sections of tissue samples make it possible to study local variation in e.g. protein expression and tumor heterogeneity by staining for a new protein in each section. In order to compare and correlate patterns of different proteins, the images have to be registered with high accuracy. The problem we want to solve is registration of gigapixel whole slide images (WSI). This presents 3 challenges: (i) Images are very large; (ii) Thin sections result in artifacts that make global affine registration prone to very large local errors; (iii) Local affine registration is required to preserve correct tissue morphology (local size, shape and texture). In our approach we compare WSI registration based on automatic and manual feature selection on either the full image or natural sub-regions (as opposed to square tiles). Working with natural sub-regions, in an interactive tool makes it possible to exclude regions containing scientifically irrelevant information. We also present a new way to visualize local registration quality by a Registration Confidence Map (RCM). With this method, intra-tumor heterogeneity and charateristics of the tumor microenvironment can be observed and quantified. |
| Tasks | Feature Selection, Image Registration |
| Published | 2019-01-24 |
| URL | http://arxiv.org/abs/1901.08317v1 |
| http://arxiv.org/pdf/1901.08317v1.pdf | |
| PWC | https://paperswithcode.com/paper/whole-slide-image-registration-for-the-study |
| Repo | |
| Framework | |
