Paper Group ANR 500
Learning the Roots of Visual Domain Shift. An approach to dealing with missing values in heterogeneous data using k-nearest neighbors. Tuning parameter calibration for $\ell_1$-regularized logistic regression. Cognitive Discriminative Mappings for Rapid Learning. Activity Networks with Delays An application to toxicity analysis. Bipolar Weighted Ar …
Learning the Roots of Visual Domain Shift
| Title | Learning the Roots of Visual Domain Shift |
| Authors | Tatiana Tommasi, Martina Lanzi, Paolo Russo, Barbara Caputo |
| Abstract | In this paper we focus on the spatial nature of visual domain shift, attempting to learn where domain adaptation originates in each given image of the source and target set. We borrow concepts and techniques from the CNN visualization literature, and learn domainnes maps able to localize the degree of domain specificity in images. We derive from these maps features related to different domainnes levels, and we show that by considering them as a preprocessing step for a domain adaptation algorithm, the final classification performance is strongly improved. Combined with the whole image representation, these features provide state of the art results on the Office dataset. |
| Tasks | Domain Adaptation |
| Published | 2016-07-20 |
| URL | http://arxiv.org/abs/1607.06144v1 |
| http://arxiv.org/pdf/1607.06144v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-the-roots-of-visual-domain-shift |
| Repo | |
| Framework | |
An approach to dealing with missing values in heterogeneous data using k-nearest neighbors
| Title | An approach to dealing with missing values in heterogeneous data using k-nearest neighbors |
| Authors | Davi E. N. Frossard, Igor O. Nunes, Renato A. Krohling |
| Abstract | Techniques such as clusterization, neural networks and decision making usually rely on algorithms that are not well suited to deal with missing values. However, real world data frequently contains such cases. The simplest solution is to either substitute them by a best guess value or completely disregard the missing values. Unfortunately, both approaches can lead to biased results. In this paper, we propose a technique for dealing with missing values in heterogeneous data using imputation based on the k-nearest neighbors algorithm. It can handle real (which we refer to as crisp henceforward), interval and fuzzy data. The effectiveness of the algorithm is tested on several datasets and the numerical results are promising. |
| Tasks | Decision Making, Imputation |
| Published | 2016-08-13 |
| URL | http://arxiv.org/abs/1608.04037v1 |
| http://arxiv.org/pdf/1608.04037v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-approach-to-dealing-with-missing-values-in |
| Repo | |
| Framework | |
Tuning parameter calibration for $\ell_1$-regularized logistic regression
| Title | Tuning parameter calibration for $\ell_1$-regularized logistic regression |
| Authors | Wei Li, Johannes Lederer |
| Abstract | Feature selection is a standard approach to understanding and modeling high-dimensional classification data, but the corresponding statistical methods hinge on tuning parameters that are difficult to calibrate. In particular, existing calibration schemes in the logistic regression framework lack any finite sample guarantees. In this paper, we introduce a novel calibration scheme for $\ell_1$-penalized logistic regression. It is based on simple tests along the tuning parameter path and is equipped with optimal guarantees for feature selection. It is also amenable to easy and efficient implementations, and it rivals or outmatches existing methods in simulations and real data applications. |
| Tasks | Calibration, Feature Selection |
| Published | 2016-10-01 |
| URL | http://arxiv.org/abs/1610.00207v2 |
| http://arxiv.org/pdf/1610.00207v2.pdf | |
| PWC | https://paperswithcode.com/paper/tuning-parameter-calibration-for-ell_1 |
| Repo | |
| Framework | |
Cognitive Discriminative Mappings for Rapid Learning
| Title | Cognitive Discriminative Mappings for Rapid Learning |
| Authors | Wen-Chieh Fang, Yi-ting Chiang |
| Abstract | Humans can learn concepts or recognize items from just a handful of examples, while machines require many more samples to perform the same task. In this paper, we build a computational model to investigate the possibility of this kind of rapid learning. The proposed method aims to improve the learning task of input from sensory memory by leveraging the information retrieved from long-term memory. We present a simple and intuitive technique called cognitive discriminative mappings (CDM) to explore the cognitive problem. First, CDM separates and clusters the data instances retrieved from long-term memory into distinct classes with a discrimination method in working memory when a sensory input triggers the algorithm. CDM then maps each sensory data instance to be as close as possible to the median point of the data group with the same class. The experimental results demonstrate that the CDM approach is effective for learning the discriminative features of supervised classifications with few training sensory input instances. |
| Tasks | |
| Published | 2016-11-08 |
| URL | http://arxiv.org/abs/1611.02512v1 |
| http://arxiv.org/pdf/1611.02512v1.pdf | |
| PWC | https://paperswithcode.com/paper/cognitive-discriminative-mappings-for-rapid |
| Repo | |
| Framework | |
Activity Networks with Delays An application to toxicity analysis
| Title | Activity Networks with Delays An application to toxicity analysis |
| Authors | Franck Delaplace, Cinzia Di Giusto, Jean-Louis Giavitto, Hanna Klaudel |
| Abstract | ANDy , Activity Networks with Delays, is a discrete time framework aimed at the qualitative modelling of time-dependent activities. The modular and concise syntax makes ANDy suitable for an easy and natural modelling of time-dependent biological systems (i.e., regulatory pathways). Activities involve entities playing the role of activators, inhibitors or products of biochemical network operation. Activities may have given duration, i.e., the time required to obtain results. An entity may represent an object (e.g., an agent, a biochemical species or a family of thereof) with a local attribute, a state denoting its level (e.g., concentration, strength). Entities levels may change as a result of an activity or may decay gradually as time passes by. The semantics of ANDy is formally given via high-level Petri nets ensuring this way some modularity. As main results we show that ANDy systems have finite state representations even for potentially infinite processes and it well adapts to the modelling of toxic behaviours. As an illustration, we present a classification of toxicity properties and give some hints on how they can be verified with existing tools on ANDy systems. A small case study on blood glucose regulation is provided to exemplify the ANDy framework and the toxicity properties. |
| Tasks | |
| Published | 2016-08-26 |
| URL | http://arxiv.org/abs/1608.07440v1 |
| http://arxiv.org/pdf/1608.07440v1.pdf | |
| PWC | https://paperswithcode.com/paper/activity-networks-with-delays-an-application |
| Repo | |
| Framework | |
Bipolar Weighted Argumentation Graphs
| Title | Bipolar Weighted Argumentation Graphs |
| Authors | Till Mossakowski, Fabian Neuhaus |
| Abstract | This paper discusses the semantics of weighted argumentation graphs that are biplor, i.e. contain both attacks and support graphs. The work builds on previous work by Amgoud, Ben-Naim et. al., which presents and compares several semantics for argumentation graphs that contain only supports or only attacks relationships, respectively. |
| Tasks | |
| Published | 2016-11-25 |
| URL | http://arxiv.org/abs/1611.08572v2 |
| http://arxiv.org/pdf/1611.08572v2.pdf | |
| PWC | https://paperswithcode.com/paper/bipolar-weighted-argumentation-graphs |
| Repo | |
| Framework | |
Revenue Forecasting for Enterprise Products
| Title | Revenue Forecasting for Enterprise Products |
| Authors | Amita Gajewar, Gagan Bansal |
| Abstract | For any business, planning is a continuous process, and typically business-owners focus on making both long-term planning aligned with a particular strategy as well as short-term planning that accommodates the dynamic market situations. An ability to perform an accurate financial forecast is crucial for effective planning. In this paper, we focus on providing an intelligent and efficient solution that will help in forecasting revenue using machine learning algorithms. We experiment with three different revenue forecasting models, and here we provide detailed insights into the methodology and their relative performance measured on real finance data. As a real-world application of our models, we partner with Microsoft’s Finance organization (department that reports Microsoft’s finances) to provide them a guidance on the projected revenue for upcoming quarters. |
| Tasks | |
| Published | 2016-11-21 |
| URL | http://arxiv.org/abs/1701.06624v1 |
| http://arxiv.org/pdf/1701.06624v1.pdf | |
| PWC | https://paperswithcode.com/paper/revenue-forecasting-for-enterprise-products |
| Repo | |
| Framework | |
Magnetic Hamiltonian Monte Carlo
| Title | Magnetic Hamiltonian Monte Carlo |
| Authors | Nilesh Tripuraneni, Mark Rowland, Zoubin Ghahramani, Richard Turner |
| Abstract | Hamiltonian Monte Carlo (HMC) exploits Hamiltonian dynamics to construct efficient proposals for Markov chain Monte Carlo (MCMC). In this paper, we present a generalization of HMC which exploits \textit{non-canonical} Hamiltonian dynamics. We refer to this algorithm as magnetic HMC, since in 3 dimensions a subset of the dynamics map onto the mechanics of a charged particle coupled to a magnetic field. We establish a theoretical basis for the use of non-canonical Hamiltonian dynamics in MCMC, and construct a symplectic, leapfrog-like integrator allowing for the implementation of magnetic HMC. Finally, we exhibit several examples where these non-canonical dynamics can lead to improved mixing of magnetic HMC relative to ordinary HMC. |
| Tasks | |
| Published | 2016-07-10 |
| URL | http://arxiv.org/abs/1607.02738v2 |
| http://arxiv.org/pdf/1607.02738v2.pdf | |
| PWC | https://paperswithcode.com/paper/magnetic-hamiltonian-monte-carlo |
| Repo | |
| Framework | |
Training variance and performance evaluation of neural networks in speech
| Title | Training variance and performance evaluation of neural networks in speech |
| Authors | Ewout van den Berg, Bhuvana Ramabhadran, Michael Picheny |
| Abstract | In this work we study variance in the results of neural network training on a wide variety of configurations in automatic speech recognition. Although this variance itself is well known, this is, to the best of our knowledge, the first paper that performs an extensive empirical study on its effects in speech recognition. We view training as sampling from a distribution and show that these distributions can have a substantial variance. These results show the urgent need to rethink the way in which results in the literature are reported and interpreted. |
| Tasks | Speech Recognition |
| Published | 2016-06-14 |
| URL | http://arxiv.org/abs/1606.04521v1 |
| http://arxiv.org/pdf/1606.04521v1.pdf | |
| PWC | https://paperswithcode.com/paper/training-variance-and-performance-evaluation |
| Repo | |
| Framework | |
Gradient Descent Only Converges to Minimizers: Non-Isolated Critical Points and Invariant Regions
| Title | Gradient Descent Only Converges to Minimizers: Non-Isolated Critical Points and Invariant Regions |
| Authors | Ioannis Panageas, Georgios Piliouras |
| Abstract | Given a non-convex twice differentiable cost function f, we prove that the set of initial conditions so that gradient descent converges to saddle points where \nabla^2 f has at least one strictly negative eigenvalue has (Lebesgue) measure zero, even for cost functions f with non-isolated critical points, answering an open question in [Lee, Simchowitz, Jordan, Recht, COLT2016]. Moreover, this result extends to forward-invariant convex subspaces, allowing for weak (non-globally Lipschitz) smoothness assumptions. Finally, we produce an upper bound on the allowable step-size. |
| Tasks | |
| Published | 2016-05-02 |
| URL | http://arxiv.org/abs/1605.00405v2 |
| http://arxiv.org/pdf/1605.00405v2.pdf | |
| PWC | https://paperswithcode.com/paper/gradient-descent-only-converges-to-minimizers |
| Repo | |
| Framework | |
Randomized Block Frank-Wolfe for Convergent Large-Scale Learning
| Title | Randomized Block Frank-Wolfe for Convergent Large-Scale Learning |
| Authors | Liang Zhang, Gang Wang, Daniel Romero, Georgios B. Giannakis |
| Abstract | Owing to their low-complexity iterations, Frank-Wolfe (FW) solvers are well suited for various large-scale learning tasks. When block-separable constraints are present, randomized block FW (RB-FW) has been shown to further reduce complexity by updating only a fraction of coordinate blocks per iteration. To circumvent the limitations of existing methods, the present work develops step sizes for RB-FW that enable a flexible selection of the number of blocks to update per iteration while ensuring convergence and feasibility of the iterates. To this end, convergence rates of RB-FW are established through computational bounds on a primal sub-optimality measure and on the duality gap. The novel bounds extend the existing convergence analysis, which only applies to a step-size sequence that does not generally lead to feasible iterates. Furthermore, two classes of step-size sequences that guarantee feasibility of the iterates are also proposed to enhance flexibility in choosing decay rates. The novel convergence results are markedly broadened to encompass also nonconvex objectives, and further assert that RB-FW with exact line-search reaches a stationary point at rate $\mathcal{O}(1/\sqrt{t})$. Performance of RB-FW with different step sizes and number of blocks is demonstrated in two applications, namely charging of electrical vehicles and structural support vector machines. Extensive simulated tests demonstrate the performance improvement of RB-FW relative to existing randomized single-block FW methods. |
| Tasks | |
| Published | 2016-12-27 |
| URL | http://arxiv.org/abs/1612.08461v2 |
| http://arxiv.org/pdf/1612.08461v2.pdf | |
| PWC | https://paperswithcode.com/paper/randomized-block-frank-wolfe-for-convergent |
| Repo | |
| Framework | |
Civique: Using Social Media to Detect Urban Emergencies
| Title | Civique: Using Social Media to Detect Urban Emergencies |
| Authors | Diptesh Kanojia, Vishwajeet Kumar, Krithi Ramamritham |
| Abstract | We present the Civique system for emergency detection in urban areas by monitoring micro blogs like Tweets. The system detects emergency related events, and classifies them into appropriate categories like “fire”, “accident”, “earthquake”, etc. We demonstrate our ideas by classifying Twitter posts in real time, visualizing the ongoing event on a map interface and alerting users with options to contact relevant authorities, both online and offline. We evaluate our classifiers for both the steps, i.e., emergency detection and categorization, and obtain F-scores exceeding 70% and 90%, respectively. We demonstrate Civique using a web interface and on an Android application, in realtime, and show its use for both tweet detection and visualization. |
| Tasks | |
| Published | 2016-10-14 |
| URL | http://arxiv.org/abs/1610.04377v1 |
| http://arxiv.org/pdf/1610.04377v1.pdf | |
| PWC | https://paperswithcode.com/paper/civique-using-social-media-to-detect-urban |
| Repo | |
| Framework | |
Measuring Player’s Behaviour Change over Time in Public Goods Game
| Title | Measuring Player’s Behaviour Change over Time in Public Goods Game |
| Authors | Polla Fattah, Uwe Aickelin, Christian Wagner |
| Abstract | An important issue in public goods game is whether player’s behaviour changes over time, and if so, how significant it is. In this game players can be classified into different groups according to the level of their participation in the public good. This problem can be considered as a concept drift problem by asking the amount of change that happens to the clusters of players over a sequence of game rounds. In this study we present a method for measuring changes in clusters with the same items over discrete time points using external clustering validation indices and area under the curve. External clustering indices were originally used to measure the difference between suggested clusters in terms of clustering algorithms and ground truth labels for items provided by experts. Instead of different cluster label comparison, we use these indices to compare between clusters of any two consecutive time points or between the first time point and the remaining time points to measure the difference between clusters through time points. In theory, any external clustering indices can be used to measure changes for any traditional (non-temporal) clustering algorithm, due to the fact that any time point alone is not carrying any temporal information. For the public goods game, our results indicate that the players are changing over time but the change is smooth and relatively constant between any two time points. |
| Tasks | |
| Published | 2016-09-09 |
| URL | http://arxiv.org/abs/1609.02672v1 |
| http://arxiv.org/pdf/1609.02672v1.pdf | |
| PWC | https://paperswithcode.com/paper/measuring-players-behaviour-change-over-time |
| Repo | |
| Framework | |
Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning
| Title | Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning |
| Authors | Tien-Ju Yang, Yu-Hsin Chen, Vivienne Sze |
| Abstract | Deep convolutional neural networks (CNNs) are indispensable to state-of-the-art computer vision algorithms. However, they are still rarely deployed on battery-powered mobile devices, such as smartphones and wearable gadgets, where vision algorithms can enable many revolutionary real-world applications. The key limiting factor is the high energy consumption of CNN processing due to its high computational complexity. While there are many previous efforts that try to reduce the CNN model size or amount of computation, we find that they do not necessarily result in lower energy consumption, and therefore do not serve as a good metric for energy cost estimation. To close the gap between CNN design and energy consumption optimization, we propose an energy-aware pruning algorithm for CNNs that directly uses energy consumption estimation of a CNN to guide the pruning process. The energy estimation methodology uses parameters extrapolated from actual hardware measurements that target realistic battery-powered system setups. The proposed layer-by-layer pruning algorithm also prunes more aggressively than previously proposed pruning methods by minimizing the error in output feature maps instead of filter weights. For each layer, the weights are first pruned and then locally fine-tuned with a closed-form least-square solution to quickly restore the accuracy. After all layers are pruned, the entire network is further globally fine-tuned using back-propagation. With the proposed pruning method, the energy consumption of AlexNet and GoogLeNet are reduced by 3.7x and 1.6x, respectively, with less than 1% top-5 accuracy loss. Finally, we show that pruning the AlexNet with a reduced number of target classes can greatly decrease the number of weights but the energy reduction is limited. Energy modeling tool and energy-aware pruned models available at http://eyeriss.mit.edu/energy.html |
| Tasks | |
| Published | 2016-11-16 |
| URL | http://arxiv.org/abs/1611.05128v4 |
| http://arxiv.org/pdf/1611.05128v4.pdf | |
| PWC | https://paperswithcode.com/paper/designing-energy-efficient-convolutional |
| Repo | |
| Framework | |
Generalized Intersection Kernel
| Title | Generalized Intersection Kernel |
| Authors | Ping Li |
| Abstract | Following the very recent line of work on the generalized min-max'' (GMM) kernel, this study proposes the generalized intersection’’ (GInt) kernel and the related normalized generalized min-max'' (NGMM) kernel. In computer vision, the (histogram) intersection kernel has been popular, and the GInt kernel generalizes it to data which can have both negative and positive entries. Through an extensive empirical classification study on 40 datasets from the UCI repository, we are able to show that this (tuning-free) GInt kernel performs fairly well. The empirical results also demonstrate that the NGMM kernel typically outperforms the GInt kernel. Interestingly, the NGMM kernel has another interpretation --- it is the asymmetrically transformed’’ version of the GInt kernel, based on the idea of ``asymmetric hashing’'. Just like the GMM kernel, the NGMM kernel can be efficiently linearized through (e.g.,) generalized consistent weighted sampling (GCWS), as empirically validated in our study. Owing to the discrete nature of hashed values, it also provides a scheme for approximate near neighbor search. | |
| Tasks | |
| Published | 2016-12-29 |
| URL | http://arxiv.org/abs/1612.09283v1 |
| http://arxiv.org/pdf/1612.09283v1.pdf | |
| PWC | https://paperswithcode.com/paper/generalized-intersection-kernel |
| Repo | |
| Framework | |
