Paper Group ANR 713
Weakly Supervised Object Discovery by Generative Adversarial & Ranking Networks. Tensor Representation in High-Frequency Financial Data for Price Change Prediction. Distribution System Voltage Control under Uncertainties using Tractable Chance Constraints. Bag-Level Aggregation for Multiple Instance Active Learning in Instance Classification Proble …
Weakly Supervised Object Discovery by Generative Adversarial & Ranking Networks
| Title | Weakly Supervised Object Discovery by Generative Adversarial & Ranking Networks |
| Authors | Ali Diba, Vivek Sharma, Rainer Stiefelhagen, Luc Van Gool |
| Abstract | The deep generative adversarial networks (GAN) recently have been shown to be promising for different computer vision applications, like image edit- ing, synthesizing high resolution images, generating videos, etc. These networks and the corresponding learning scheme can handle various visual space map- pings. We approach GANs with a novel training method and learning objective, to discover multiple object instances for three cases: 1) synthesizing a picture of a specific object within a cluttered scene; 2) localizing different categories in images for weakly supervised object detection; and 3) improving object discov- ery in object detection pipelines. A crucial advantage of our method is that it learns a new deep similarity metric, to distinguish multiple objects in one im- age. We demonstrate that the network can act as an encoder-decoder generating parts of an image which contain an object, or as a modified deep CNN to rep- resent images for object detection in supervised and weakly supervised scheme. Our ranking GAN offers a novel way to search through images for object specific patterns. We have conducted experiments for different scenarios and demonstrate the method performance for object synthesizing and weakly supervised object detection and classification using the MS-COCO and PASCAL VOC datasets. |
| Tasks | Object Detection, Weakly Supervised Object Detection |
| Published | 2017-11-22 |
| URL | http://arxiv.org/abs/1711.08174v2 |
| http://arxiv.org/pdf/1711.08174v2.pdf | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-object-discovery-by |
| Repo | |
| Framework | |
Tensor Representation in High-Frequency Financial Data for Price Change Prediction
| Title | Tensor Representation in High-Frequency Financial Data for Price Change Prediction |
| Authors | Dat Thanh Tran, Martin Magris, Juho Kanniainen, Moncef Gabbouj, Alexandros Iosifidis |
| Abstract | Nowadays, with the availability of massive amount of trade data collected, the dynamics of the financial markets pose both a challenge and an opportunity for high frequency traders. In order to take advantage of the rapid, subtle movement of assets in High Frequency Trading (HFT), an automatic algorithm to analyze and detect patterns of price change based on transaction records must be available. The multichannel, time-series representation of financial data naturally suggests tensor-based learning algorithms. In this work, we investigate the effectiveness of two multilinear methods for the mid-price prediction problem against other existing methods. The experiments in a large scale dataset which contains more than 4 millions limit orders show that by utilizing tensor representation, multilinear models outperform vector-based approaches and other competing ones. |
| Tasks | Time Series |
| Published | 2017-09-05 |
| URL | http://arxiv.org/abs/1709.01268v4 |
| http://arxiv.org/pdf/1709.01268v4.pdf | |
| PWC | https://paperswithcode.com/paper/tensor-representation-in-high-frequency |
| Repo | |
| Framework | |
Distribution System Voltage Control under Uncertainties using Tractable Chance Constraints
| Title | Distribution System Voltage Control under Uncertainties using Tractable Chance Constraints |
| Authors | Pan Li, Baihong Jin, Dai Wang, Baosen Zhang |
| Abstract | Voltage control plays an important role in the operation of electricity distribution networks, especially with high penetration of distributed energy resources. These resources introduce significant and fast varying uncertainties. In this paper, we focus on reactive power compensation to control voltage in the presence of uncertainties. We adopt a chance constraint approach that accounts for arbitrary correlations between renewable resources at each of the buses. We show how the problem can be solved efficiently using historical samples via a stochastic quasi gradient method. We also show that this optimization problem is convex for a wide variety of probabilistic distributions. Compared to conventional per-bus chance constraints, our formulation is more robust to uncertainty and more computationally tractable. We illustrate the results using standard IEEE distribution test feeders. |
| Tasks | |
| Published | 2017-04-28 |
| URL | http://arxiv.org/abs/1704.08999v4 |
| http://arxiv.org/pdf/1704.08999v4.pdf | |
| PWC | https://paperswithcode.com/paper/distribution-system-voltage-control-under |
| Repo | |
| Framework | |
Bag-Level Aggregation for Multiple Instance Active Learning in Instance Classification Problems
| Title | Bag-Level Aggregation for Multiple Instance Active Learning in Instance Classification Problems |
| Authors | Marc-André Carbonneau, Eric Granger, Ghyslain Gagnon |
| Abstract | A growing number of applications, e.g. video surveillance and medical image analysis, require training recognition systems from large amounts of weakly annotated data while some targeted interactions with a domain expert are allowed to improve the training process. In such cases, active learning (AL) can reduce labeling costs for training a classifier by querying the expert to provide the labels of most informative instances. This paper focuses on AL methods for instance classification problems in multiple instance learning (MIL), where data is arranged into sets, called bags, that are weakly labeled. Most AL methods focus on single instance learning problems. These methods are not suitable for MIL problems because they cannot account for the bag structure of data. In this paper, new methods for bag-level aggregation of instance informativeness are proposed for multiple instance active learning (MIAL). The \textit{aggregated informativeness} method identifies the most informative instances based on classifier uncertainty, and queries bags incorporating the most information. The other proposed method, called \textit{cluster-based aggregative sampling}, clusters data hierarchically in the instance space. The informativeness of instances is assessed by considering bag labels, inferred instance labels, and the proportion of labels that remain to be discovered in clusters. Both proposed methods significantly outperform reference methods in extensive experiments using benchmark data from several application domains. Results indicate that using an appropriate strategy to address MIAL problems yields a significant reduction in the number of queries needed to achieve the same level of performance as single instance AL methods. |
| Tasks | Active Learning, Multiple Instance Learning |
| Published | 2017-10-06 |
| URL | http://arxiv.org/abs/1710.02584v1 |
| http://arxiv.org/pdf/1710.02584v1.pdf | |
| PWC | https://paperswithcode.com/paper/bag-level-aggregation-for-multiple-instance |
| Repo | |
| Framework | |
Balanced Policy Evaluation and Learning
| Title | Balanced Policy Evaluation and Learning |
| Authors | Nathan Kallus |
| Abstract | We present a new approach to the problems of evaluating and learning personalized decision policies from observational data of past contexts, decisions, and outcomes. Only the outcome of the enacted decision is available and the historical policy is unknown. These problems arise in personalized medicine using electronic health records and in internet advertising. Existing approaches use inverse propensity weighting (or, doubly robust versions) to make historical outcome (or, residual) data look like it were generated by a new policy being evaluated or learned. But this relies on a plug-in approach that rejects data points with a decision that disagrees with the new policy, leading to high variance estimates and ineffective learning. We propose a new, balance-based approach that too makes the data look like the new policy but does so directly by finding weights that optimize for balance between the weighted data and the target policy in the given, finite sample, which is equivalent to minimizing worst-case or posterior conditional mean square error. Our policy learner proceeds as a two-level optimization problem over policies and weights. We demonstrate that this approach markedly outperforms existing ones both in evaluation and learning, which is unsurprising given the wider support of balance-based weights. We establish extensive theoretical consistency guarantees and regret bounds that support this empirical success. |
| Tasks | |
| Published | 2017-05-21 |
| URL | https://arxiv.org/abs/1705.07384v2 |
| https://arxiv.org/pdf/1705.07384v2.pdf | |
| PWC | https://paperswithcode.com/paper/balanced-policy-evaluation-and-learning |
| Repo | |
| Framework | |
A reliability-based approach for influence maximization using the evidence theory
| Title | A reliability-based approach for influence maximization using the evidence theory |
| Authors | Siwar Jendoubi, Arnaud Martin |
| Abstract | The influence maximization is the problem of finding a set of social network users, called influencers, that can trigger a large cascade of propagation. Influencers are very beneficial to make a marketing campaign goes viral through social networks for example. In this paper, we propose an influence measure that combines many influence indicators. Besides, we consider the reliability of each influence indicator and we present a distance-based process that allows to estimate the reliability of each indicator. The proposed measure is defined under the framework of the theory of belief functions. Furthermore, the reliability-based influence measure is used with an influence maximization model to select a set of users that are able to maximize the influence in the network. Finally, we present a set of experiments on a dataset collected from Twitter. These experiments show the performance of the proposed solution in detecting social influencers with good quality. |
| Tasks | |
| Published | 2017-06-30 |
| URL | http://arxiv.org/abs/1706.10188v1 |
| http://arxiv.org/pdf/1706.10188v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-reliability-based-approach-for-influence |
| Repo | |
| Framework | |
Variational approach for learning Markov processes from time series data
| Title | Variational approach for learning Markov processes from time series data |
| Authors | Hao Wu, Frank Noé |
| Abstract | Inference, prediction and control of complex dynamical systems from time series is important in many areas, including financial markets, power grid management, climate and weather modeling, or molecular dynamics. The analysis of such highly nonlinear dynamical systems is facilitated by the fact that we can often find a (generally nonlinear) transformation of the system coordinates to features in which the dynamics can be excellently approximated by a linear Markovian model. Moreover, the large number of system variables often change collectively on large time- and length-scales, facilitating a low-dimensional analysis in feature space. In this paper, we introduce a variational approach for Markov processes (VAMP) that allows us to find optimal feature mappings and optimal Markovian models of the dynamics from given time series data. The key insight is that the best linear model can be obtained from the top singular components of the Koopman operator. This leads to the definition of a family of score functions called VAMP-r which can be calculated from data, and can be employed to optimize a Markovian model. In addition, based on the relationship between the variational scores and approximation errors of Koopman operators, we propose a new VAMP-E score, which can be applied to cross-validation for hyper-parameter optimization and model selection in VAMP. VAMP is valid for both reversible and nonreversible processes and for stationary and non-stationary processes or realizations. |
| Tasks | Model Selection, Time Series |
| Published | 2017-07-14 |
| URL | https://arxiv.org/abs/1707.04659v3 |
| https://arxiv.org/pdf/1707.04659v3.pdf | |
| PWC | https://paperswithcode.com/paper/variational-approach-for-learning-markov |
| Repo | |
| Framework | |
Causality-Aided Falsification
| Title | Causality-Aided Falsification |
| Authors | Takumi Akazaki, Yoshihiro Kumazawa, Ichiro Hasuo |
| Abstract | Falsification is drawing attention in quality assurance of heterogeneous systems whose complexities are beyond most verification techniques’ scalability. In this paper we introduce the idea of causality aid in falsification: by providing a falsification solver – that relies on stochastic optimization of a certain cost function – with suitable causal information expressed by a Bayesian network, search for a falsifying input value can be efficient. Our experiment results show the idea’s viability. |
| Tasks | Stochastic Optimization |
| Published | 2017-09-08 |
| URL | http://arxiv.org/abs/1709.02555v1 |
| http://arxiv.org/pdf/1709.02555v1.pdf | |
| PWC | https://paperswithcode.com/paper/causality-aided-falsification |
| Repo | |
| Framework | |
Orthogonal Machine Learning: Power and Limitations
| Title | Orthogonal Machine Learning: Power and Limitations |
| Authors | Lester Mackey, Vasilis Syrgkanis, Ilias Zadik |
| Abstract | Double machine learning provides $\sqrt{n}$-consistent estimates of parameters of interest even when high-dimensional or nonparametric nuisance parameters are estimated at an $n^{-1/4}$ rate. The key is to employ Neyman-orthogonal moment equations which are first-order insensitive to perturbations in the nuisance parameters. We show that the $n^{-1/4}$ requirement can be improved to $n^{-1/(2k+2)}$ by employing a $k$-th order notion of orthogonality that grants robustness to more complex or higher-dimensional nuisance parameters. In the partially linear regression setting popular in causal inference, we show that we can construct second-order orthogonal moments if and only if the treatment residual is not normally distributed. Our proof relies on Stein’s lemma and may be of independent interest. We conclude by demonstrating the robustness benefits of an explicit doubly-orthogonal estimation procedure for treatment effect. |
| Tasks | Causal Inference |
| Published | 2017-11-01 |
| URL | http://arxiv.org/abs/1711.00342v6 |
| http://arxiv.org/pdf/1711.00342v6.pdf | |
| PWC | https://paperswithcode.com/paper/orthogonal-machine-learning-power-and |
| Repo | |
| Framework | |
A Genetic Algorithm-Based Solver for Very Large Jigsaw Puzzles
| Title | A Genetic Algorithm-Based Solver for Very Large Jigsaw Puzzles |
| Authors | Dror Sholomon, Eli David, Nathan S. Netanyahu |
| Abstract | In this paper we propose the first effective automated, genetic algorithm (GA)-based jigsaw puzzle solver. We introduce a novel procedure of merging two “parent” solutions to an improved “child” solution by detecting, extracting, and combining correctly assembled puzzle segments. The solver proposed exhibits state-of-the-art performance solving previously attempted puzzles faster and far more accurately, and also puzzles of size never before attempted. Other contributions include the creation of a benchmark of large images, previously unavailable. We share the data sets and all of our results for future testing and comparative evaluation of jigsaw puzzle solvers. |
| Tasks | |
| Published | 2017-11-17 |
| URL | http://arxiv.org/abs/1711.06769v1 |
| http://arxiv.org/pdf/1711.06769v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-genetic-algorithm-based-solver-for-very |
| Repo | |
| Framework | |
Asking the Difficult Questions: Goal-Oriented Visual Question Generation via Intermediate Rewards
| Title | Asking the Difficult Questions: Goal-Oriented Visual Question Generation via Intermediate Rewards |
| Authors | Junjie Zhang, Qi Wu, Chunhua Shen, Jian Zhang, Jianfeng Lu, Anton van den Hengel |
| Abstract | Despite significant progress in a variety of vision-and-language problems, developing a method capable of asking intelligent, goal-oriented questions about images is proven to be an inscrutable challenge. Towards this end, we propose a Deep Reinforcement Learning framework based on three new intermediate rewards, namely goal-achieved, progressive and informativeness that encourage the generation of succinct questions, which in turn uncover valuable information towards the overall goal. By directly optimizing for questions that work quickly towards fulfilling the overall goal, we avoid the tendency of existing methods to generate long series of insane queries that add little value. We evaluate our model on the GuessWhat?! dataset and show that the resulting questions can help a standard Guesser identify a specific object in an image at a much higher success rate. |
| Tasks | Question Generation |
| Published | 2017-11-21 |
| URL | http://arxiv.org/abs/1711.07614v1 |
| http://arxiv.org/pdf/1711.07614v1.pdf | |
| PWC | https://paperswithcode.com/paper/asking-the-difficult-questions-goal-oriented |
| Repo | |
| Framework | |
Deriving Quests from Open World Mechanics
| Title | Deriving Quests from Open World Mechanics |
| Authors | Ryan Alexander, Chris Martens |
| Abstract | Open world games present players with more freedom than games with linear progression structures. However, without clearly-defined objectives, they often leave players without a sense of purpose. Most of the time, quests and objectives are hand-authored and overlaid atop an open world’s mechanics. But what if they could be generated organically from the gameplay itself? The goal of our project was to develop a model of the mechanics in Minecraft that could be used to determine the ideal placement of objectives in an open world setting. We formalized the game logic of Minecraft in terms of logical rules that can be manipulated in two ways: they may be executed to generate graphs representative of the player experience when playing an open world game with little developer direction; and they may be statically analyzed to determine dependency orderings, feedback loops, and bottlenecks. These analyses may then be used to place achievements on gameplay actions algorithmically. |
| Tasks | |
| Published | 2017-04-30 |
| URL | http://arxiv.org/abs/1705.00341v1 |
| http://arxiv.org/pdf/1705.00341v1.pdf | |
| PWC | https://paperswithcode.com/paper/deriving-quests-from-open-world-mechanics |
| Repo | |
| Framework | |
BoostJet: Towards Combining Statistical Aggregates with Neural Embeddings for Recommendations
| Title | BoostJet: Towards Combining Statistical Aggregates with Neural Embeddings for Recommendations |
| Authors | Rhicheek Patra, Egor Samosvat, Michael Roizner, Andrei Mishchenko |
| Abstract | Recommenders have become widely popular in recent years because of their broader applicability in many e-commerce applications. These applications rely on recommenders for generating advertisements for various offers or providing content recommendations. However, the quality of the generated recommendations depends on user features (like demography, temporality), offer features (like popularity, price), and user-offer features (like implicit or explicit feedback). Current state-of-the-art recommenders do not explore such diverse features concurrently while generating the recommendations. In this paper, we first introduce the notion of Trackers which enables us to capture the above-mentioned features and thus incorporate users’ online behaviour through statistical aggregates of different features (demography, temporality, popularity, price). We also show how to capture offer-to-offer relations, based on their consumption sequence, leveraging neural embeddings for offers in our Offer2Vec algorithm. We then introduce BoostJet, a novel recommender which integrates the Trackers along with the neural embeddings using MatrixNet, an efficient distributed implementation of gradient boosted decision tree, to improve the recommendation quality significantly. We provide an in-depth evaluation of BoostJet on Yandex’s dataset, collecting online behaviour from tens of millions of online users, to demonstrate the practicality of BoostJet in terms of recommendation quality as well as scalability. |
| Tasks | |
| Published | 2017-11-15 |
| URL | http://arxiv.org/abs/1711.05828v2 |
| http://arxiv.org/pdf/1711.05828v2.pdf | |
| PWC | https://paperswithcode.com/paper/boostjet-towards-combining-statistical |
| Repo | |
| Framework | |
Response to “Counterexample to global convergence of DSOS and SDSOS hierarchies”
| Title | Response to “Counterexample to global convergence of DSOS and SDSOS hierarchies” |
| Authors | Amir Ali Ahmadi, Anirudha Majumdar |
| Abstract | In a recent note [8], the author provides a counterexample to the global convergence of what his work refers to as “the DSOS and SDSOS hierarchies” for polynomial optimization problems (POPs) and purports that this refutes claims in our extended abstract [4] and slides in [3]. The goal of this paper is to clarify that neither [4], nor [3], and certainly not our full paper [5], ever defined DSOS or SDSOS hierarchies as it is done in [8]. It goes without saying that no claims about convergence properties of the hierarchies in [8] were ever made as a consequence. What was stated in [4,3] was completely different: we stated that there exist hierarchies based on DSOS and SDSOS optimization that converge. This is indeed true as we discuss in this response. We also emphasize that we were well aware that some (S)DSOS hierarchies do not converge even if their natural SOS counterparts do. This is readily implied by an example in our prior work [5], which makes the counterexample in [8] superfluous. Finally, we provide concrete counterarguments to claims made in [8] that aim to challenge the scalability improvements obtained by DSOS and SDSOS optimization as compared to sum of squares (SOS) optimization. [3] A. A. Ahmadi and A. Majumdar. DSOS and SDSOS: More tractable alternatives to SOS. Slides at the meeting on Geometry and Algebra of Linear Matrix Inequalities, CIRM, Marseille, 2013. [4] A. A. Ahmadi and A. Majumdar. DSOS and SDSOS optimization: LP and SOCP-based alternatives to sum of squares optimization. In proceedings of the 48th annual IEEE Conference on Information Sciences and Systems, 2014. [5] A. A. Ahmadi and A. Majumdar. DSOS and SDSOS optimization: more tractable alternatives to sum of squares and semidefinite optimization. arXiv:1706.02586, 2017. [8] C. Josz. Counterexample to global convergence of DSOS and SDSOS hierarchies. arXiv:1707.02964, 2017. |
| Tasks | |
| Published | 2017-10-09 |
| URL | http://arxiv.org/abs/1710.02901v1 |
| http://arxiv.org/pdf/1710.02901v1.pdf | |
| PWC | https://paperswithcode.com/paper/response-to-counterexample-to-global |
| Repo | |
| Framework | |
Independently Controllable Features
| Title | Independently Controllable Features |
| Authors | Emmanuel Bengio, Valentin Thomas, Joelle Pineau, Doina Precup, Yoshua Bengio |
| Abstract | Finding features that disentangle the different causes of variation in real data is a difficult task, that has nonetheless received considerable attention in static domains like natural images. Interactive environments, in which an agent can deliberately take actions, offer an opportunity to tackle this task better, because the agent can experiment with different actions and observe their effects. We introduce the idea that in interactive environments, latent factors that control the variation in observed data can be identified by figuring out what the agent can control. We propose a naive method to find factors that explain or measure the effect of the actions of a learner, and test it in illustrative experiments. |
| Tasks | |
| Published | 2017-03-22 |
| URL | http://arxiv.org/abs/1703.07718v1 |
| http://arxiv.org/pdf/1703.07718v1.pdf | |
| PWC | https://paperswithcode.com/paper/independently-controllable-features |
| Repo | |
| Framework | |
