Paper Group ANR 623
Contextual Search via Intrinsic Volumes. Comparing Fairness Criteria Based on Social Outcome. Deep Neural Networks for Choice Analysis: Extracting Complete Economic Information for Interpretation. Learning to Classify from Impure Samples with High-Dimensional Data. Texture Deformation Based Generative Adversarial Networks for Face Editing. Deep Ste …
Contextual Search via Intrinsic Volumes
Title | Contextual Search via Intrinsic Volumes |
Authors | Renato Paes Leme, Jon Schneider |
Abstract | We study the problem of contextual search, a multidimensional generalization of binary search that captures many problems in contextual decision-making. In contextual search, a learner is trying to learn the value of a hidden vector $v \in [0,1]^d$. Every round the learner is provided an adversarially-chosen context $u_t \in \mathbb{R}^d$, submits a guess $p_t$ for the value of $\langle u_t, v\rangle$, learns whether $p_t < \langle u_t, v\rangle$, and incurs loss $\ell(\langle u_t, v\rangle, p_t)$ (for some loss function $\ell$). The learner’s goal is to minimize their total loss over the course of $T$ rounds. We present an algorithm for the contextual search problem for the symmetric loss function $\ell(\theta, p) = \theta - p$ that achieves $O_{d}(1)$ total loss. We present a new algorithm for the dynamic pricing problem (which can be realized as a special case of the contextual search problem) that achieves $O_{d}(\log \log T)$ total loss, improving on the previous best known upper bounds of $O_{d}(\log T)$ and matching the known lower bounds (up to a polynomial dependence on $d$). Both algorithms make significant use of ideas from the field of integral geometry, most notably the notion of intrinsic volumes of a convex set. To the best of our knowledge this is the first application of intrinsic volumes to algorithm design. |
Tasks | Decision Making |
Published | 2018-04-09 |
URL | http://arxiv.org/abs/1804.03195v2 |
http://arxiv.org/pdf/1804.03195v2.pdf | |
PWC | https://paperswithcode.com/paper/contextual-search-via-intrinsic-volumes |
Repo | |
Framework | |
Comparing Fairness Criteria Based on Social Outcome
Title | Comparing Fairness Criteria Based on Social Outcome |
Authors | Junpei Komiyama, Hajime Shimao |
Abstract | Fairness in algorithmic decision-making processes is attracting increasing concern. When an algorithm is applied to human-related decision-making an estimator solely optimizing its predictive power can learn biases on the existing data, which motivates us the notion of fairness in machine learning. while several different notions are studied in the literature, little studies are done on how these notions affect the individuals. We demonstrate such a comparison between several policies induced by well-known fairness criteria, including the color-blind (CB), the demographic parity (DP), and the equalized odds (EO). We show that the EO is the only criterion among them that removes group-level disparity. Empirical studies on the social welfare and disparity of these policies are conducted. |
Tasks | Decision Making |
Published | 2018-06-13 |
URL | http://arxiv.org/abs/1806.05112v1 |
http://arxiv.org/pdf/1806.05112v1.pdf | |
PWC | https://paperswithcode.com/paper/comparing-fairness-criteria-based-on-social |
Repo | |
Framework | |
Deep Neural Networks for Choice Analysis: Extracting Complete Economic Information for Interpretation
Title | Deep Neural Networks for Choice Analysis: Extracting Complete Economic Information for Interpretation |
Authors | Shenhao Wang, Qingyi Wang, Jinhua Zhao |
Abstract | While deep neural networks (DNNs) have been increasingly applied to choice analysis showing high predictive power, it is unclear to what extent researchers can interpret economic information from DNNs. This paper demonstrates that DNNs can provide economic information as complete as classical discrete choice models (DCMs). The economic information includes choice predictions, choice probabilities, market shares, substitution patterns of alternatives, social welfare, probability derivatives, elasticities, marginal rates of substitution (MRS), and heterogeneous values of time (VOT). Unlike DCMs, DNNs can automatically learn the utility function and reveal behavioral patterns that are not prespecified by domain experts. However, the economic information obtained from DNNs can be unreliable because of the three challenges associated with the automatic learning capacity: high sensitivity to hyperparameters, model non-identification, and local irregularity. To demonstrate the strength and challenges of DNNs, we estimated the DNNs using a stated preference survey, extracted the full list of economic information from the DNNs, and compared them with those from the DCMs. We found that the economic information either aggregated over trainings or population is more reliable than the disaggregate information of the individual observations or trainings, and that even simple hyperparameter searching can significantly improve the reliability of the economic information extracted from the DNNs. Future studies should investigate other regularizations and DNN architectures, better optimization algorithms, and robust DNN training methods to address DNNs’ three challenges, to provide more reliable economic information from DNN-based choice models. |
Tasks | |
Published | 2018-12-11 |
URL | https://arxiv.org/abs/1812.04528v2 |
https://arxiv.org/pdf/1812.04528v2.pdf | |
PWC | https://paperswithcode.com/paper/using-deep-neural-network-to-analyze-travel |
Repo | |
Framework | |
Learning to Classify from Impure Samples with High-Dimensional Data
Title | Learning to Classify from Impure Samples with High-Dimensional Data |
Authors | Patrick T. Komiske, Eric M. Metodiev, Benjamin Nachman, Matthew D. Schwartz |
Abstract | A persistent challenge in practical classification tasks is that labeled training sets are not always available. In particle physics, this challenge is surmounted by the use of simulations. These simulations accurately reproduce most features of data, but cannot be trusted to capture all of the complex correlations exploitable by modern machine learning methods. Recent work in weakly supervised learning has shown that simple, low-dimensional classifiers can be trained using only the impure mixtures present in data. Here, we demonstrate that complex, high-dimensional classifiers can also be trained on impure mixtures using weak supervision techniques, with performance comparable to what could be achieved with pure samples. Using weak supervision will therefore allow us to avoid relying exclusively on simulations for high-dimensional classification. This work opens the door to a new regime whereby complex models are trained directly on data, providing direct access to probe the underlying physics. |
Tasks | |
Published | 2018-01-30 |
URL | http://arxiv.org/abs/1801.10158v2 |
http://arxiv.org/pdf/1801.10158v2.pdf | |
PWC | https://paperswithcode.com/paper/learning-to-classify-from-impure-samples-with |
Repo | |
Framework | |
Texture Deformation Based Generative Adversarial Networks for Face Editing
Title | Texture Deformation Based Generative Adversarial Networks for Face Editing |
Authors | WenTing Chen, Xinpeng Xie, Xi Jia, Linlin Shen |
Abstract | Despite the significant success in image-to-image translation and latent representation based facial attribute editing and expression synthesis, the existing approaches still have limitations in the sharpness of details, distinct image translation and identity preservation. To address these issues, we propose a Texture Deformation Based GAN, namely TDB-GAN, to disentangle texture from original image and transfers domains based on the extracted texture. The approach utilizes the texture to transfer facial attributes and expressions without the consideration of the object pose. This leads to shaper details and more distinct visual effect of the synthesized faces. In addition, it brings the faster convergence during training. The effectiveness of the proposed method is validated through extensive ablation studies. We also evaluate our approach qualitatively and quantitatively on facial attribute and facial expression synthesis. The results on both the CelebA and RaFD datasets suggest that Texture Deformation Based GAN achieves better performance. |
Tasks | Image-to-Image Translation |
Published | 2018-12-24 |
URL | http://arxiv.org/abs/1812.09832v1 |
http://arxiv.org/pdf/1812.09832v1.pdf | |
PWC | https://paperswithcode.com/paper/texture-deformation-based-generative |
Repo | |
Framework | |
Deep Steganalysis: End-to-End Learning with Supervisory Information beyond Class Labels
Title | Deep Steganalysis: End-to-End Learning with Supervisory Information beyond Class Labels |
Authors | Wei Wang, Jing Dong, Yinlong Qian, Tieniu Tan |
Abstract | Recently, deep learning has shown its power in steganalysis. However, the proposed deep models have been often learned from pre-calculated noise residuals with fixed high-pass filters rather than from raw images. In this paper, we propose a new end-to-end learning framework that can learn steganalytic features directly from pixels. In the meantime, the high-pass filters are also automatically learned. Besides class labels, we make use of additional pixel level supervision of cover-stego image pair to jointly and iteratively train the proposed network which consists of a residual calculation network and a steganalysis network. The experimental results prove the effectiveness of the proposed architecture. |
Tasks | |
Published | 2018-06-27 |
URL | http://arxiv.org/abs/1806.10443v1 |
http://arxiv.org/pdf/1806.10443v1.pdf | |
PWC | https://paperswithcode.com/paper/deep-steganalysis-end-to-end-learning-with |
Repo | |
Framework | |
Linear Memory Networks
Title | Linear Memory Networks |
Authors | Davide Bacciu, Antonio Carta, Alessandro Sperduti |
Abstract | Recurrent neural networks can learn complex transduction problems that require maintaining and actively exploiting a memory of their inputs. Such models traditionally consider memory and input-output functionalities indissolubly entangled. We introduce a novel recurrent architecture based on the conceptual separation between the functional input-output transformation and the memory mechanism, showing how they can be implemented through different neural components. By building on such conceptualization, we introduce the Linear Memory Network, a recurrent model comprising a feedforward neural network, realizing the non-linear functional transformation, and a linear autoencoder for sequences, implementing the memory component. The resulting architecture can be efficiently trained by building on closed-form solutions to linear optimization problems. Further, by exploiting equivalence results between feedforward and recurrent neural networks we devise a pretraining schema for the proposed architecture. Experiments on polyphonic music datasets show competitive results against gated recurrent networks and other state of the art models. |
Tasks | |
Published | 2018-11-08 |
URL | http://arxiv.org/abs/1811.03356v1 |
http://arxiv.org/pdf/1811.03356v1.pdf | |
PWC | https://paperswithcode.com/paper/linear-memory-networks |
Repo | |
Framework | |
Reliable counting of weakly labeled concepts by a single spiking neuron model
Title | Reliable counting of weakly labeled concepts by a single spiking neuron model |
Authors | Hannes Rapp, Martin Paul Nawrot, Merav Stern |
Abstract | Making an informed, correct and quick decision can be life-saving. It’s crucial for animals during an escape behaviour or for autonomous cars during driving. The decision can be complex and may involve an assessment of the amount of threats present and the nature of each threat. Thus, we should expect early sensory processing to supply classification information fast and accurately, even before relying the information to higher brain areas or more complex system components downstream. Today, advanced convolutional artificial neural networks can successfully solve visual detection and classification tasks and are commonly used to build complex decision making systems. However, in order to perform well on these tasks they require increasingly complex, “very deep” model structure, which is costly in inference run-time, energy consumption and number of training samples, only trainable on cloud-computing clusters. A single spiking neuron has been shown to be able to solve recognition tasks for homogeneous Poisson input statistics, a commonly used model for spiking activity in the neocortex. When modeled as leaky integrate and fire with gradient decent learning algorithm it was shown to posses a variety of complex computational capabilities. Here we improve its implementation. We also account for more natural stimulus generated inputs that deviate from this homogeneous Poisson spiking. The improved gradient-based local learning rule allows for significantly better and stable generalization. We also show that with its improved capabilities it can count weakly labeled concepts by applying our model to a problem of multiple instance learning (MIL) with counting where labels are only available for collections of concepts. In this counting MNIST task the neuron exploits the improved implementation and outperforms conventional ConvNet architecture under similar condtions. |
Tasks | Decision Making, Multiple Instance Learning |
Published | 2018-05-19 |
URL | http://arxiv.org/abs/1805.07569v2 |
http://arxiv.org/pdf/1805.07569v2.pdf | |
PWC | https://paperswithcode.com/paper/reliable-counting-of-weakly-labeled-concepts |
Repo | |
Framework | |
Composite Marginal Likelihood Methods for Random Utility Models
Title | Composite Marginal Likelihood Methods for Random Utility Models |
Authors | Zhibing Zhao, Lirong Xia |
Abstract | We propose a novel and flexible rank-breaking-then-composite-marginal-likelihood (RBCML) framework for learning random utility models (RUMs), which include the Plackett-Luce model. We characterize conditions for the objective function of RBCML to be strictly log-concave by proving that strict log-concavity is preserved under convolution and marginalization. We characterize necessary and sufficient conditions for RBCML to satisfy consistency and asymptotic normality. Experiments on synthetic data show that RBCML for Gaussian RUMs achieves better statistical efficiency and computational efficiency than the state-of-the-art algorithm and our RBCML for the Plackett-Luce model provides flexible tradeoffs between running time and statistical efficiency. |
Tasks | |
Published | 2018-06-04 |
URL | http://arxiv.org/abs/1806.01426v1 |
http://arxiv.org/pdf/1806.01426v1.pdf | |
PWC | https://paperswithcode.com/paper/composite-marginal-likelihood-methods-for |
Repo | |
Framework | |
Empirical Risk Minimization in Non-interactive Local Differential Privacy: Efficiency and High Dimensional Case
Title | Empirical Risk Minimization in Non-interactive Local Differential Privacy: Efficiency and High Dimensional Case |
Authors | Di Wang, Marco Gaboardi, Jinhui Xu |
Abstract | In this paper, we study the Empirical Risk Minimization problem in the non-interactive local model of differential privacy. In the case of constant or low dimensionality ($p\ll n$), we first show that if the ERM loss function is $(\infty, T)$-smooth, then we can avoid a dependence of the sample complexity, to achieve error $\alpha$, on the exponential of the dimensionality $p$ with base $1/\alpha$ (i.e., $\alpha^{-p}$), which answers a question in [smith 2017 interaction]. Our approach is based on polynomial approximation. Then, we propose player-efficient algorithms with $1$-bit communication complexity and $O(1)$ computation cost for each player. The error bound is asymptotically the same as the original one. Also with additional assumptions we show a server efficient algorithm. Next we consider the high dimensional case ($n\ll p$), we show that if the loss function is Generalized Linear function and convex, then we could get an error bound which is dependent on the Gaussian width of the underlying constrained set instead of $p$, which is lower than that in [smith 2017 interaction]. |
Tasks | |
Published | 2018-02-12 |
URL | http://arxiv.org/abs/1802.04085v3 |
http://arxiv.org/pdf/1802.04085v3.pdf | |
PWC | https://paperswithcode.com/paper/empirical-risk-minimization-in-non-1 |
Repo | |
Framework | |
Isolated and Ensemble Audio Preprocessing Methods for Detecting Adversarial Examples against Automatic Speech Recognition
Title | Isolated and Ensemble Audio Preprocessing Methods for Detecting Adversarial Examples against Automatic Speech Recognition |
Authors | Krishan Rajaratnam, Kunal Shah, Jugal Kalita |
Abstract | An adversarial attack is an exploitative process in which minute alterations are made to natural inputs, causing the inputs to be misclassified by neural models. In the field of speech recognition, this has become an issue of increasing significance. Although adversarial attacks were originally introduced in computer vision, they have since infiltrated the realm of speech recognition. In 2017, a genetic attack was shown to be quite potent against the Speech Commands Model. Limited-vocabulary speech classifiers, such as the Speech Commands Model, are used in a variety of applications, particularly in telephony; as such, adversarial examples produced by this attack pose as a major security threat. This paper explores various methods of detecting these adversarial examples with combinations of audio preprocessing. One particular combined defense incorporating compressions, speech coding, filtering, and audio panning was shown to be quite effective against the attack on the Speech Commands Model, detecting audio adversarial examples with 93.5% precision and 91.2% recall. |
Tasks | Adversarial Attack, Speech Recognition |
Published | 2018-09-11 |
URL | http://arxiv.org/abs/1809.04397v1 |
http://arxiv.org/pdf/1809.04397v1.pdf | |
PWC | https://paperswithcode.com/paper/isolated-and-ensemble-audio-preprocessing |
Repo | |
Framework | |
Discrete linear-complexity reinforcement learning in continuous action spaces for Q-learning algorithms
Title | Discrete linear-complexity reinforcement learning in continuous action spaces for Q-learning algorithms |
Authors | Peyman Tavallali, Gary B. Doran Jr., Lukas Mandrake |
Abstract | In this article, we sketch an algorithm that extends the Q-learning algorithms to the continuous action space domain. Our method is based on the discretization of the action space. Despite the commonly used discretization methods, our method does not increase the discretized problem dimensionality exponentially. We will show that our proposed method is linear in complexity when the discretization is employed. The variant of the Q-learning algorithm presented in this work, labeled as Finite Step Q-Learning (FSQ), can be deployed to both shallow and deep neural network architectures. |
Tasks | Q-Learning |
Published | 2018-07-16 |
URL | http://arxiv.org/abs/1807.06957v2 |
http://arxiv.org/pdf/1807.06957v2.pdf | |
PWC | https://paperswithcode.com/paper/discrete-linear-complexity-reinforcement |
Repo | |
Framework | |
Open the Black Box Data-Driven Explanation of Black Box Decision Systems
Title | Open the Black Box Data-Driven Explanation of Black Box Decision Systems |
Authors | Dino Pedreschi, Fosca Giannotti, Riccardo Guidotti, Anna Monreale, Luca Pappalardo, Salvatore Ruggieri, Franco Turini |
Abstract | Black box systems for automated decision making, often based on machine learning over (big) data, map a user’s features into a class or a score without exposing the reasons why. This is problematic not only for lack of transparency, but also for possible biases hidden in the algorithms, due to human prejudices and collection artifacts hidden in the training data, which may lead to unfair or wrong decisions. We introduce the local-to-global framework for black box explanation, a novel approach with promising early results, which paves the road for a wide spectrum of future developments along three dimensions: (i) the language for expressing explanations in terms of highly expressive logic-based rules, with a statistical and causal interpretation; (ii) the inference of local explanations aimed at revealing the logic of the decision adopted for a specific instance by querying and auditing the black box in the vicinity of the target instance; (iii), the bottom-up generalization of the many local explanations into simple global ones, with algorithms that optimize the quality and comprehensibility of explanations. |
Tasks | Decision Making |
Published | 2018-06-26 |
URL | http://arxiv.org/abs/1806.09936v1 |
http://arxiv.org/pdf/1806.09936v1.pdf | |
PWC | https://paperswithcode.com/paper/open-the-black-box-data-driven-explanation-of |
Repo | |
Framework | |
The Potential of the Return Distribution for Exploration in RL
Title | The Potential of the Return Distribution for Exploration in RL |
Authors | Thomas M. Moerland, Joost Broekens, Catholijn M. Jonker |
Abstract | This paper studies the potential of the return distribution for exploration in deterministic reinforcement learning (RL) environments. We study network losses and propagation mechanisms for Gaussian, Categorical and Gaussian mixture distributions. Combined with exploration policies that leverage this return distribution, we solve, for example, a randomized Chain task of length 100, which has not been reported before when learning with neural networks. |
Tasks | |
Published | 2018-06-11 |
URL | http://arxiv.org/abs/1806.04242v2 |
http://arxiv.org/pdf/1806.04242v2.pdf | |
PWC | https://paperswithcode.com/paper/the-potential-of-the-return-distribution-for |
Repo | |
Framework | |
Robust Spoken Language Understanding via Paraphrasing
Title | Robust Spoken Language Understanding via Paraphrasing |
Authors | Avik Ray, Yilin Shen, Hongxia Jin |
Abstract | Learning intents and slot labels from user utterances is a fundamental step in all spoken language understanding (SLU) and dialog systems. State-of-the-art neural network based methods, after deployment, often suffer from performance degradation on encountering paraphrased utterances, and out-of-vocabulary words, rarely observed in their training set. We address this challenging problem by introducing a novel paraphrasing based SLU model which can be integrated with any existing SLU model in order to improve their overall performance. We propose two new paraphrase generators using RNN and sequence-to-sequence based neural networks, which are suitable for our application. Our experiments on existing benchmark and in house datasets demonstrate the robustness of our models to rare and complex paraphrased utterances, even under adversarial test distributions. |
Tasks | Spoken Language Understanding |
Published | 2018-09-17 |
URL | http://arxiv.org/abs/1809.06444v1 |
http://arxiv.org/pdf/1809.06444v1.pdf | |
PWC | https://paperswithcode.com/paper/robust-spoken-language-understanding-via |
Repo | |
Framework | |