Paper Group ANR 925
Language Tasks and Language Games: On Methodology in Current Natural Language Processing Research. Greedy Algorithms for Fair Division of Mixed Manna. Flood Detection On Low Cost Orbital Hardware. An Adaptive Deep Learning Algorithm Based Autoencoder for Interference Channels. A learning-based algorithm to quickly compute good primal solutions for …
Language Tasks and Language Games: On Methodology in Current Natural Language Processing Research
| Title | Language Tasks and Language Games: On Methodology in Current Natural Language Processing Research |
| Authors | David Schlangen |
| Abstract | “This paper introduces a new task and a new dataset”, “we improve the state of the art in X by Y” – it is rare to find a current natural language processing paper (or AI paper more generally) that does not contain such statements. What is mostly left implicit, however, is the assumption that this necessarily constitutes progress, and what it constitutes progress towards. Here, we make more precise the normally impressionistically used notions of language task and language game and ask how a research programme built on these might make progress towards the goal of modelling general language competence. |
| Tasks | |
| Published | 2019-08-28 |
| URL | https://arxiv.org/abs/1908.10747v1 |
| https://arxiv.org/pdf/1908.10747v1.pdf | |
| PWC | https://paperswithcode.com/paper/language-tasks-and-language-games-on |
| Repo | |
| Framework | |
Greedy Algorithms for Fair Division of Mixed Manna
| Title | Greedy Algorithms for Fair Division of Mixed Manna |
| Authors | Martin Aleksandrov, Toby Walsh |
| Abstract | We consider a multi-agent model for fair division of mixed manna (i.e. items for which agents can have positive, zero or negative utilities), in which agents have additive utilities for bundles of items. For this model, we give several general impossibility results and special possibility results for three common fairness concepts (i.e. EF1, EFX, EFX3) and one popular efficiency concept (i.e. PO). We also study how these interact with common welfare objectives such as the Nash, disutility Nash and egalitarian welfares. For example, we show that maximizing the Nash welfare with mixed manna (or minimizing the disutility Nash welfare) does not ensure an EF1 allocation whereas with goods and the Nash welfare it does. We also prove that an EFX3 allocation may not exist even with identical utilities. By comparison, with tertiary utilities, EFX and PO allocations, or EFX3 and PO allocations always exist. Also, with identical utilities, EFX and PO allocations always exist. For these cases, we give polynomial-time algorithms, returning such allocations and approximating further the Nash, disutility Nash and egalitarian welfares in special cases. |
| Tasks | |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.11005v2 |
| https://arxiv.org/pdf/1911.11005v2.pdf | |
| PWC | https://paperswithcode.com/paper/greedy-algorithms-for-fair-division-of-mixed |
| Repo | |
| Framework | |
Flood Detection On Low Cost Orbital Hardware
| Title | Flood Detection On Low Cost Orbital Hardware |
| Authors | Gonzalo Mateo-Garcia, Silviu Oprea, Lewis Smith, Josh Veitch-Michaelis, Guy Schumann, Yarin Gal, Atılım Güneş Baydin, Dietmar Backes |
| Abstract | Satellite imaging is a critical technology for monitoring and responding to natural disasters such as flooding. Despite the capabilities of modern satellites, there is still much to be desired from the perspective of first response organisations like UNICEF. Two main challenges are rapid access to data, and the ability to automatically identify flooded regions in images. We describe a prototypical flood segmentation system, identifying cloud, water and land, that could be deployed on a constellation of small satellites, performing processing on board to reduce downlink bandwidth by 2 orders of magnitude. We target PhiSat-1, part of the FSSCAT mission, which is planned to be launched by the European Space Agency (ESA) near the start of 2020 as a proof of concept for this new technology. |
| Tasks | |
| Published | 2019-10-04 |
| URL | https://arxiv.org/abs/1910.03019v3 |
| https://arxiv.org/pdf/1910.03019v3.pdf | |
| PWC | https://paperswithcode.com/paper/flood-detection-on-low-cost-orbital-hardware |
| Repo | |
| Framework | |
An Adaptive Deep Learning Algorithm Based Autoencoder for Interference Channels
| Title | An Adaptive Deep Learning Algorithm Based Autoencoder for Interference Channels |
| Authors | Dehao Wu, Maziar Nekovee, Yue Wang |
| Abstract | Deep learning (DL) based autoencoder has shown great potential to significantly enhance the physical layer performance. In this paper, we present a DL based autoencoder for interference channel. Based on a characterization of a k-user Gaussian interference channel, where the interferences are classified as different levels from weak to very strong interferences based on a coupling parameter {\alpha}, a DL neural network (NN) based autoencoder is designed to train the data set and decode the received signals. The performance such a DL autoencoder for different interference scenarios are studied, with {\alpha} known or partially known, where we assume that {\alpha} is predictable but with a varying up to 10% at the training stage. The results demonstrate that DL based approach has a significant capability to mitigate the effect induced by a poor signal-to-noise ratio (SNR) and a high interference-to-noise ratio (INR). However, the enhancement depends on the knowledge of {\alpha} as well as the interference levels. The proposed DL approach performs well with {\alpha} up to 10% offset for weak interference level. For strong and very strong interference channel, the offset of {\alpha} needs to be constrained to less than 5% and 2%, respectively, to maintain similar performance as {\alpha} is known. |
| Tasks | |
| Published | 2019-02-18 |
| URL | https://arxiv.org/abs/1902.06841v2 |
| https://arxiv.org/pdf/1902.06841v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-based-autoencoder-for |
| Repo | |
| Framework | |
A learning-based algorithm to quickly compute good primal solutions for Stochastic Integer Programs
| Title | A learning-based algorithm to quickly compute good primal solutions for Stochastic Integer Programs |
| Authors | Yoshua Bengio, Emma Frejinger, Andrea Lodi, Rahul Patel, Sriram Sankaranarayanan |
| Abstract | We propose a novel approach using supervised learning to obtain near-optimal primal solutions for two-stage stochastic integer programming (2SIP) problems with constraints in the first and second stages. The goal of the algorithm is to predict a “representative scenario” (RS) for the problem such that, deterministically solving the 2SIP with the random realization equal to the RS, gives a near-optimal solution to the original 2SIP. Predicting an RS, instead of directly predicting a solution ensures first-stage feasibility of the solution. If the problem is known to have complete recourse, second-stage feasibility is also guaranteed. For computational testing, we learn to find an RS for a two-stage stochastic facility location problem with integer variables and linear constraints in both stages and consistently provide near-optimal solutions. Our computing times are very competitive with those of general-purpose integer programming solvers to achieve a similar solution quality. |
| Tasks | |
| Published | 2019-12-17 |
| URL | https://arxiv.org/abs/1912.08112v1 |
| https://arxiv.org/pdf/1912.08112v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-learning-based-algorithm-to-quickly-compute |
| Repo | |
| Framework | |
Active strict saddles in nonsmooth optimization
| Title | Active strict saddles in nonsmooth optimization |
| Authors | Damek Davis, Dmitriy Drusvyatskiy |
| Abstract | We introduce a geometrically transparent strict saddle property for nonsmooth functions. This property guarantees that simple proximal algorithms on weakly convex problems converge only to local minimizers, when randomly initialized. We argue that the strict saddle property may be a realistic assumption in applications, since it provably holds for generic semi-algebraic optimization problems. |
| Tasks | |
| Published | 2019-12-16 |
| URL | https://arxiv.org/abs/1912.07146v1 |
| https://arxiv.org/pdf/1912.07146v1.pdf | |
| PWC | https://paperswithcode.com/paper/active-strict-saddles-in-nonsmooth |
| Repo | |
| Framework | |
Random Tessellation Forests
| Title | Random Tessellation Forests |
| Authors | Shufei Ge, Shijia Wang, Yee Whye Teh, Liangliang Wang, Lloyd T. Elliott |
| Abstract | Space partitioning methods such as random forests and the Mondrian process are powerful machine learning methods for multi-dimensional and relational data, and are based on recursively cutting a domain. The flexibility of these methods is often limited by the requirement that the cuts be axis aligned. The Ostomachion process and the self-consistent binary space partitioning-tree process were recently introduced as generalizations of the Mondrian process for space partitioning with non-axis aligned cuts in the two dimensional plane. Motivated by the need for a multi-dimensional partitioning tree with non-axis aligned cuts, we propose the Random Tessellation Process (RTP), a framework that includes the Mondrian process and the binary space partitioning-tree process as special cases. We derive a sequential Monte Carlo algorithm for inference, and provide random forest methods. Our process is self-consistent and can relax axis-aligned constraints, allowing complex inter-dimensional dependence to be captured. We present a simulation study, and analyse gene expression data of brain tissue, showing improved accuracies over other methods. |
| Tasks | |
| Published | 2019-06-13 |
| URL | https://arxiv.org/abs/1906.05440v5 |
| https://arxiv.org/pdf/1906.05440v5.pdf | |
| PWC | https://paperswithcode.com/paper/random-tessellation-forests |
| Repo | |
| Framework | |
Exploring the Hyperparameter Landscape of Adversarial Robustness
| Title | Exploring the Hyperparameter Landscape of Adversarial Robustness |
| Authors | Evelyn Duesterwald, Anupama Murthi, Ganesh Venkataraman, Mathieu Sinn, Deepak Vijaykeerthy |
| Abstract | Adversarial training shows promise as an approach for training models that are robust towards adversarial perturbation. In this paper, we explore some of the practical challenges of adversarial training. We present a sensitivity analysis that illustrates that the effectiveness of adversarial training hinges on the settings of a few salient hyperparameters. We show that the robustness surface that emerges across these salient parameters can be surprisingly complex and that therefore no effective one-size-fits-all parameter settings exist. We then demonstrate that we can use the same salient hyperparameters as tuning knob to navigate the tension that can arise between robustness and accuracy. Based on these findings, we present a practical approach that leverages hyperparameter optimization techniques for tuning adversarial training to maximize robustness while keeping the loss in accuracy within a defined budget. |
| Tasks | Hyperparameter Optimization |
| Published | 2019-05-09 |
| URL | https://arxiv.org/abs/1905.03837v1 |
| https://arxiv.org/pdf/1905.03837v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-the-hyperparameter-landscape-of |
| Repo | |
| Framework | |
QRMODA and BRMODA: Novel Models for Face Recognition Accuracy in Computer Vision Systems with Adapted Video Streams
| Title | QRMODA and BRMODA: Novel Models for Face Recognition Accuracy in Computer Vision Systems with Adapted Video Streams |
| Authors | Hayder Hamandi, Nabil Sarhan |
| Abstract | A major challenge facing Computer Vision systems is providing the ability to accurately detect threats and recognize subjects and/or objects under dynamically changing network conditions. We propose two novel models that characterize the face recognition accuracy in terms of video encoding parameters. Specifically, we model the accuracy in terms of video resolution, quantization, and actual bit rate. We validate the models using two distinct video datasets and a large image dataset by conducting 1, 668 experiments that involve simultaneously varying combinations of encoding parameters. We show that both models hold true for the deep learning and statistical based face recognition. Furthermore, we show that the models can be used to capture different accuracy metrics, specifically the recall, precision, and F1-score. Ultimately, we provide meaningful insights on the factors affecting the constants of each proposed model. |
| Tasks | Accuracy Metrics, Face Recognition, Quantization |
| Published | 2019-07-24 |
| URL | https://arxiv.org/abs/1907.10559v1 |
| https://arxiv.org/pdf/1907.10559v1.pdf | |
| PWC | https://paperswithcode.com/paper/qrmoda-and-brmoda-novel-models-for-face |
| Repo | |
| Framework | |
Reinforcement Learning with Chromatic Networks for Compact Architecture Search
| Title | Reinforcement Learning with Chromatic Networks for Compact Architecture Search |
| Authors | Xingyou Song, Krzysztof Choromanski, Jack Parker-Holder, Yunhao Tang, Wenbo Gao, Aldo Pacchiano, Tamas Sarlos, Deepali Jain, Yuxiang Yang |
| Abstract | We present a neural architecture search algorithm to construct compact reinforcement learning (RL) policies, by combining ENAS and ES in a highly scalable and intuitive way. By defining the combinatorial search space of NAS to be the set of different edge-partitionings (colorings) into same-weight classes, we represent compact architectures via efficient learned edge-partitionings. For several RL tasks, we manage to learn colorings translating to effective policies parameterized by as few as $17$ weight parameters, providing >90% compression over vanilla policies and 6x compression over state-of-the-art compact policies based on Toeplitz matrices, while still maintaining good reward. We believe that our work is one of the first attempts to propose a rigorous approach to training structured neural network architectures for RL problems that are of interest especially in mobile robotics with limited storage and computational resources. |
| Tasks | Combinatorial Optimization, Neural Architecture Search |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.06511v3 |
| https://arxiv.org/pdf/1907.06511v3.pdf | |
| PWC | https://paperswithcode.com/paper/reinforcement-learning-with-chromatic |
| Repo | |
| Framework | |
Data Markets to support AI for All: Pricing, Valuation and Governance
| Title | Data Markets to support AI for All: Pricing, Valuation and Governance |
| Authors | Ramesh Raskar, Praneeth Vepakomma, Tristan Swedish, Aalekh Sharan |
| Abstract | We discuss a data market technique based on intrinsic (relevance and uniqueness) as well as extrinsic value (influenced by supply and demand) of data. For intrinsic value, we explain how to perform valuation of data in absolute terms (i.e just by itself), or relatively (i.e in comparison to multiple datasets) or in conditional terms (i.e valuating new data given currently existing data). |
| Tasks | |
| Published | 2019-05-14 |
| URL | https://arxiv.org/abs/1905.06462v1 |
| https://arxiv.org/pdf/1905.06462v1.pdf | |
| PWC | https://paperswithcode.com/paper/data-markets-to-support-ai-for-all-pricing |
| Repo | |
| Framework | |
A Finite-Sample Deviation Bound for Stable Autoregressive Processes
| Title | A Finite-Sample Deviation Bound for Stable Autoregressive Processes |
| Authors | Rodrigo A. González, Cristian R. Rojas |
| Abstract | In this paper, we study non-asymptotic deviation bounds of the least squares estimator in Gaussian AR($n$) processes. By relying on martingale concentration inequalities and a tail-bound for $\chi^2$ distributed variables, we provide a concentration bound for the sample covariance matrix of the process output. With this, we present a problem-dependent finite-time bound on the deviation probability of any fixed linear combination of the estimated parameters of the AR$(n)$ process. We discuss extensions and limitations of our approach. |
| Tasks | |
| Published | 2019-12-17 |
| URL | https://arxiv.org/abs/1912.08103v1 |
| https://arxiv.org/pdf/1912.08103v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-finite-sample-deviation-bound-for-stable |
| Repo | |
| Framework | |
Multimodal Self-Supervised Learning for Medical Image Analysis
| Title | Multimodal Self-Supervised Learning for Medical Image Analysis |
| Authors | Aiham Taleb, Christoph Lippert, Tassilo Klein, Moin Nabi |
| Abstract | In this paper, we propose a self-supervised learning approach that leverages multiple imaging modalities to increase data efficiency for medical image analysis. To this end, we introduce multimodal puzzle-solving proxy tasks, which facilitate neural network representation learning from multiple image modalities. These representations allow for subsequent fine-tuning on different downstream tasks. To achieve that, we employ the Sinkhorn operator to predict permutations of puzzle pieces in conjunction with a modality agnostic feature embedding. Together, they allow for a lean network architecture and increased computational efficiency. Under this framework, we propose different strategies for puzzle construction, integrating multiple medical imaging modalities, with varying levels of puzzle complexity. We benchmark these strategies in a range of experiments to assess the gains of our method in downstream performance and data-efficiency on different target tasks. Our experiments show that solving puzzles interleaved with multimodal content yields more powerful semantic representations. This allows us to solve downstream tasks more accurately and efficiently, compared to treating each modality independently. We demonstrate the effectiveness of the proposed approach on two multimodal medical imaging benchmarks: the BraTS and the Prostate semantic segmentation datasets, on which we achieve competitive results to state-of-the-art solutions, at a fraction of the computational expense. We also outperform many previous solutions on the chosen benchmarks. |
| Tasks | Representation Learning, Semantic Segmentation |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.05396v1 |
| https://arxiv.org/pdf/1912.05396v1.pdf | |
| PWC | https://paperswithcode.com/paper/multimodal-self-supervised-learning-for |
| Repo | |
| Framework | |
Hebbian Synaptic Modifications in Spiking Neurons that Learn
| Title | Hebbian Synaptic Modifications in Spiking Neurons that Learn |
| Authors | Peter L. Bartlett, Jonathan Baxter |
| Abstract | In this paper, we derive a new model of synaptic plasticity, based on recent algorithms for reinforcement learning (in which an agent attempts to learn appropriate actions to maximize its long-term average reward). We show that these direct reinforcement learning algorithms also give locally optimal performance for the problem of reinforcement learning with multiple agents, without any explicit communication between agents. By considering a network of spiking neurons as a collection of agents attempting to maximize the long-term average of a reward signal, we derive a synaptic update rule that is qualitatively similar to Hebb’s postulate. This rule requires only simple computations, such as addition and leaky integration, and involves only quantities that are available in the vicinity of the synapse. Furthermore, it leads to synaptic connection strengths that give locally optimal values of the long term average reward. The reinforcement learning paradigm is sufficiently broad to encompass many learning problems that are solved by the brain. We illustrate, with simulations, that the approach is effective for simple pattern classification and motor learning tasks. |
| Tasks | |
| Published | 2019-11-17 |
| URL | https://arxiv.org/abs/1911.07247v1 |
| https://arxiv.org/pdf/1911.07247v1.pdf | |
| PWC | https://paperswithcode.com/paper/hebbian-synaptic-modifications-in-spiking |
| Repo | |
| Framework | |
Casting Light on Invisible Cities: Computationally Engaging with Literary Criticism
| Title | Casting Light on Invisible Cities: Computationally Engaging with Literary Criticism |
| Authors | Shufan Wang, Mohit Iyyer |
| Abstract | Literary critics often attempt to uncover meaning in a single work of literature through careful reading and analysis. Applying natural language processing methods to aid in such literary analyses remains a challenge in digital humanities. While most previous work focuses on “distant reading” by algorithmically discovering high-level patterns from large collections of literary works, here we sharpen the focus of our methods to a single literary theory about Italo Calvino’s postmodern novel Invisible Cities, which consists of 55 short descriptions of imaginary cities. Calvino has provided a classification of these cities into eleven thematic groups, but literary scholars disagree as to how trustworthy his categorization is. Due to the unique structure of this novel, we can computationally weigh in on this debate: we leverage pretrained contextualized representations to embed each city’s description and use unsupervised methods to cluster these embeddings. Additionally, we compare results of our computational approach to similarity judgments generated by human readers. Our work is a first step towards incorporating natural language processing into literary criticism. |
| Tasks | |
| Published | 2019-04-17 |
| URL | http://arxiv.org/abs/1904.08386v1 |
| http://arxiv.org/pdf/1904.08386v1.pdf | |
| PWC | https://paperswithcode.com/paper/casting-light-on-invisible-cities |
| Repo | |
| Framework | |
