Paper Group ANR 1142
Random projections: data perturbation for classification problems. Computational Separations between Sampling and Optimization. Optimal Farsighted Agents Tend to Seek Power. High-Throughput Machine Learning from Electronic Health Records. Machine learning and serving of discrete field theories – when artificial intelligence meets the discrete univ …
Random projections: data perturbation for classification problems
| Title | Random projections: data perturbation for classification problems |
| Authors | Timothy I. Cannings |
| Abstract | Random projections offer an appealing and flexible approach to a wide range of large-scale statistical problems. They are particularly useful in high-dimensional settings, where we have many covariates recorded for each observation. In classification problems there are two general techniques using random projections. The first involves many projections in an ensemble – the idea here is to aggregate the results after applying different random projections, with the aim of achieving superior statistical accuracy. The second class of methods include hashing and sketching techniques, which are straightforward ways to reduce the complexity of a problem, perhaps therefore with a huge computational saving, while approximately preserving the statistical efficiency. |
| Tasks | |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.10800v1 |
| https://arxiv.org/pdf/1911.10800v1.pdf | |
| PWC | https://paperswithcode.com/paper/random-projections-data-perturbation-for |
| Repo | |
| Framework | |
Computational Separations between Sampling and Optimization
| Title | Computational Separations between Sampling and Optimization |
| Authors | Kunal Talwar |
| Abstract | Two commonly arising computational tasks in Bayesian learning are Optimization (Maximum A Posteriori estimation) and Sampling (from the posterior distribution). In the convex case these two problems are efficiently reducible to each other. Recent work (Ma et al. 2019) shows that in the non-convex case, sampling can sometimes be provably faster. We present a simpler and stronger separation. We then compare sampling and optimization in more detail and show that they are provably incomparable: there are families of continuous functions for which optimization is easy but sampling is NP-hard, and vice versa. Further, we show function families that exhibit a sharp phase transition in the computational complexity of sampling, as one varies the natural temperature parameter. Our results draw on a connection to analogous separations in the discrete setting which are well-studied. |
| Tasks | |
| Published | 2019-11-05 |
| URL | https://arxiv.org/abs/1911.02074v1 |
| https://arxiv.org/pdf/1911.02074v1.pdf | |
| PWC | https://paperswithcode.com/paper/computational-separations-between-sampling |
| Repo | |
| Framework | |
Optimal Farsighted Agents Tend to Seek Power
| Title | Optimal Farsighted Agents Tend to Seek Power |
| Authors | Alexander Matt Turner |
| Abstract | Some researchers have speculated that capable reinforcement learning (RL) agents pursuing misspecified objectives are often incentivized to seek resources and power in pursuit of those objectives. An agent seeking power is incentivized to behave in undesirable ways, including rationally preventing deactivation and correction. Others have voiced skepticism: humans seem idiosyncratic in their urges to power, which need not be present in the agents we design. We formalize a notion of power within the context of finite deterministic Markov decision processes (MDPs). We prove that, with respect to a neutral class of reward function distributions, optimal policies tend to seek power over the environment. |
| Tasks | |
| Published | 2019-12-03 |
| URL | https://arxiv.org/abs/1912.01683v2 |
| https://arxiv.org/pdf/1912.01683v2.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-farsighted-agents-tend-to-seek-power |
| Repo | |
| Framework | |
High-Throughput Machine Learning from Electronic Health Records
| Title | High-Throughput Machine Learning from Electronic Health Records |
| Authors | Ross S. Kleiman, Paul S. Bennett, Peggy L. Peissig, Richard L. Berg, Zhaobin Kuang, Scott J. Hebbring, Michael D. Caldwell, David Page |
| Abstract | The widespread digitization of patient data via electronic health records (EHRs) has created an unprecedented opportunity to use machine learning algorithms to better predict disease risk at the patient level. Although predictive models have previously been constructed for a few important diseases, such as breast cancer and myocardial infarction, we currently know very little about how accurately the risk for most diseases or events can be predicted, and how far in advance. Machine learning algorithms use training data rather than preprogrammed rules to make predictions and are well suited for the complex task of disease prediction. Although there are thousands of conditions and illnesses patients can encounter, no prior research simultaneously predicts risks for thousands of diagnosis codes and thereby establishes a comprehensive patient risk profile. Here we show that such pandiagnostic prediction is possible with a high level of performance across diagnosis codes. For the tasks of predicting diagnosis risks both 1 and 6 months in advance, we achieve average areas under the receiver operating characteristic curve (AUCs) of 0.803 and 0.758, respectively, across thousands of prediction tasks. Finally, our research contributes a new clinical prediction dataset in which researchers can explore how well a diagnosis can be predicted and what health factors are most useful for prediction. For the first time, we can get a much more complete picture of how well risks for thousands of different diagnosis codes can be predicted. |
| Tasks | Disease Prediction |
| Published | 2019-07-03 |
| URL | https://arxiv.org/abs/1907.01901v1 |
| https://arxiv.org/pdf/1907.01901v1.pdf | |
| PWC | https://paperswithcode.com/paper/high-throughput-machine-learning-from |
| Repo | |
| Framework | |
Machine learning and serving of discrete field theories – when artificial intelligence meets the discrete universe
| Title | Machine learning and serving of discrete field theories – when artificial intelligence meets the discrete universe |
| Authors | Hong Qin |
| Abstract | A method for machine learning and serving of discrete field theories in physics is developed. The learning algorithm trains a discrete field theory from a set of observational data on a spacetime lattice, and the serving algorithm uses the learned discrete field theory to predict new observations of the field for new boundary and initial conditions. The approach to learn discrete field theories overcomes the difficulties associated with learning continuous theories by artificial intelligence. The serving algorithm of discrete field theories belongs to the family of structure-preserving geometric algorithms, which have been proven to be superior to the conventional algorithms based on discretization of differential equations. The effectiveness of the method and algorithms developed is demonstrated using the examples of nonlinear oscillations and the Kepler problem. In particular, the learning algorithm learns a discrete field theory from a set of data of planetary orbits similar to what Kepler inherited from Tycho Brahe in 1601, and the serving algorithm correctly predicts other planetary orbits, including parabolic and hyperbolic escaping orbits, of the solar system without learning or knowing Newton’s laws of motion and universal gravitation. The proposed algorithms are also applicable when effects of special relativity and general relativity are important. The illustrated advantages of discrete field theories relative to continuous theories in terms of machine learning compatibility are consistent with Bostrom’s simulation hypothesis. |
| Tasks | |
| Published | 2019-10-22 |
| URL | https://arxiv.org/abs/1910.10147v2 |
| https://arxiv.org/pdf/1910.10147v2.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-and-serving-of-discrete |
| Repo | |
| Framework | |
Differential Scene Flow from Light Field Gradients
| Title | Differential Scene Flow from Light Field Gradients |
| Authors | Sizhuo Ma, Brandon M. Smith, Mohit Gupta |
| Abstract | This paper presents novel techniques for recovering 3D dense scene flow, based on differential analysis of 4D light fields. The key enabling result is a per-ray linear equation, called the ray flow equation, that relates 3D scene flow to 4D light field gradients. The ray flow equation is invariant to 3D scene structure and applicable to a general class of scenes, but is under-constrained (3 unknowns per equation). Thus, additional constraints must be imposed to recover motion. We develop two families of scene flow algorithms by leveraging the structural similarity between ray flow and optical flow equations: local ‘Lucas-Kanade’ ray flow and global ‘Horn-Schunck’ ray flow, inspired by corresponding optical flow methods. We also develop a combined local-global method by utilizing the correspondence structure in the light fields. We demonstrate high precision 3D scene flow recovery for a wide range of scenarios, including rotation and non-rigid motion. We analyze the theoretical and practical performance limits of the proposed techniques via the light field structure tensor, a 3x3 matrix that encodes the local structure of light fields. We envision that the proposed analysis and algorithms will lead to design of future light-field cameras that are optimized for motion sensing, in addition to depth sensing. |
| Tasks | Optical Flow Estimation |
| Published | 2019-07-26 |
| URL | https://arxiv.org/abs/1907.11637v2 |
| https://arxiv.org/pdf/1907.11637v2.pdf | |
| PWC | https://paperswithcode.com/paper/differential-scene-flow-from-light-field |
| Repo | |
| Framework | |
Classifier Chains: A Review and Perspectives
| Title | Classifier Chains: A Review and Perspectives |
| Authors | Jesse Read, Bernhard Pfahringer, Geoff Holmes, Eibe Frank |
| Abstract | The family of methods collectively known as classifier chains has become a popular approach to multi-label learning problems. This approach involves linking together off-the-shelf binary classifiers in a chain structure, such that class label predictions become features for other classifiers. Such methods have proved flexible and effective and have obtained state-of-the-art empirical performance across many datasets and multi-label evaluation metrics. This performance led to further studies of how exactly it works, and how it could be improved, and in the recent decade numerous studies have explored classifier chains mechanisms on a theoretical level, and many improvements have been made to the training and inference procedures, such that this method remains among the state-of-the-art options for multi-label learning. Given this past and ongoing interest, which covers a broad range of applications and research themes, the goal of this work is to provide a review of classifier chains, a survey of the techniques and extensions provided in the literature, as well as perspectives for this approach in the domain of multi-label classification in the future. We conclude positively, with a number of recommendations for researchers and practitioners, as well as outlining a number of areas for future research. |
| Tasks | Multi-Label Classification, Multi-Label Learning |
| Published | 2019-12-26 |
| URL | https://arxiv.org/abs/1912.13405v1 |
| https://arxiv.org/pdf/1912.13405v1.pdf | |
| PWC | https://paperswithcode.com/paper/classifier-chains-a-review-and-perspectives |
| Repo | |
| Framework | |
Relationship-Embedded Representation Learning for Grounding Referring Expressions
| Title | Relationship-Embedded Representation Learning for Grounding Referring Expressions |
| Authors | Sibei Yang, Guanbin Li, Yizhou Yu |
| Abstract | Grounding referring expressions in images aims to locate the object instance in an image described by a referring expression. It involves a joint understanding of natural language and image content, and is essential for a range of visual tasks related to human-computer interaction. As a language-to-vision matching task, the core of this problem is to not only extract all the necessary information (i.e., objects and the relationships among them) in both the image and referring expression, but also make full use of context information to align cross-modal semantic concepts in the extracted information. Unfortunately, existing work on grounding referring expressions fails to accurately extract multi-order relationships from the referring expression and associate them with the objects and their related contexts in the image. In this paper, we propose a Cross-Modal Relationship Extractor (CMRE) to adaptively highlight objects and relationships (spatial and semantic relations) related to the given expression with a cross-modal attention mechanism, and represent the extracted information as a language-guided visual relation graph. In addition, we propose a Gated Graph Convolutional Network (GGCN) to compute multimodal semantic contexts by fusing information from different modes and propagating multimodal information in the structured relation graph. Experimental results on three common benchmark datasets show that our Cross-Modal Relationship Inference Network, which consists of CMRE and GGCN, significantly surpasses all existing state-of-the-art methods. |
| Tasks | Representation Learning |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1906.04464v2 |
| https://arxiv.org/pdf/1906.04464v2.pdf | |
| PWC | https://paperswithcode.com/paper/cross-modal-relationship-inference-for-1 |
| Repo | |
| Framework | |
Learning Query Inseparable ELH Ontologies
| Title | Learning Query Inseparable ELH Ontologies |
| Authors | Ana Ozaki, Cosimo Persia, Andrea Mazzullo |
| Abstract | We investigate the complexity of learning query inseparable ELH ontologies in a variant of Angluin’s exact learning model. Given a fixed data instance A* and a query language Q, we are interested in computing an ontology H that entails the same queries as a target ontology T on A*, that is, H and T are inseparable w.r.t. A* and Q. The learner is allowed to pose two kinds of questions. The first is Does (T,A)\models q?', with A an arbitrary data instance and q and query in Q. An oracle replies this question with yes’ or no'. In the second, the learner asks Are H and T inseparable w.r.t. A* and Q?'. If so, the learning process finishes, otherwise, the learner receives (A*,q) with q in Q, (T,A*)\models q and (H,A*)\not\models q (or vice-versa). Then, we analyse conditions in which query inseparability is preserved if A* changes. Finally, we consider the PAC learning model and a setting where the algorithms learn from a batch of classified data, limiting interactions with the oracles. |
| Tasks | |
| Published | 2019-11-17 |
| URL | https://arxiv.org/abs/1911.07229v2 |
| https://arxiv.org/pdf/1911.07229v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-query-inseparable-elh-ontologies |
| Repo | |
| Framework | |
Generative Audio Synthesis with a Parametric Model
| Title | Generative Audio Synthesis with a Parametric Model |
| Authors | Krishna Subramani, Alexandre D’Hooge, Preeti Rao |
| Abstract | Use a parametric representation of audio to train a generative model in the interest of obtaining more flexible control over the generated sound. |
| Tasks | |
| Published | 2019-11-15 |
| URL | https://arxiv.org/abs/1911.08335v1 |
| https://arxiv.org/pdf/1911.08335v1.pdf | |
| PWC | https://paperswithcode.com/paper/generative-audio-synthesis-with-a-parametric |
| Repo | |
| Framework | |
Transfer Learning using CNN for Handwritten Devanagari Character Recognition
| Title | Transfer Learning using CNN for Handwritten Devanagari Character Recognition |
| Authors | Nagender Aneja, Sandhya Aneja |
| Abstract | This paper presents an analysis of pre-trained models to recognize handwritten Devanagari alphabets using transfer learning for Deep Convolution Neural Network (DCNN). This research implements AlexNet, DenseNet, Vgg, and Inception ConvNet as a fixed feature extractor. We implemented 15 epochs for each of AlexNet, DenseNet 121, DenseNet 201, Vgg 11, Vgg 16, Vgg 19, and Inception V3. Results show that Inception V3 performs better in terms of accuracy achieving 99% accuracy with average epoch time 16.3 minutes while AlexNet performs fastest with 2.2 minutes per epoch and achieving 98% accuracy. |
| Tasks | Transfer Learning |
| Published | 2019-09-19 |
| URL | https://arxiv.org/abs/1909.08774v1 |
| https://arxiv.org/pdf/1909.08774v1.pdf | |
| PWC | https://paperswithcode.com/paper/transfer-learning-using-cnn-for-handwritten |
| Repo | |
| Framework | |
Decentralized Deep Reinforcement Learning for Delay-Power Tradeoff in Vehicular Communications
| Title | Decentralized Deep Reinforcement Learning for Delay-Power Tradeoff in Vehicular Communications |
| Authors | Xianfu Chen, Celimuge Wu, Honggang Zhang, Yan Zhang, Mehdi Bennis, Heli Vuojala |
| Abstract | This paper targets at the problem of radio resource management for expected long-term delay-power tradeoff in vehicular communications. At each decision epoch, the road side unit observes the global network state, allocates channels and schedules data packets for all vehicle user equipment-pairs (VUE-pairs). The decision-making procedure is modelled as a discrete-time Markov decision process (MDP). The technical challenges in solving an optimal control policy originate from highly spatial mobility of vehicles and temporal variations in data traffic. To simplify the decision-making process, we first decompose the MDP into a series of per-VUE-pair MDPs. We then propose an online long short-term memory based deep reinforcement learning algorithm to break the curse of high dimensionality in state space faced by each per-VUE-pair MDP. With the proposed algorithm, the optimal channel allocation and packet scheduling decision at each epoch can be made in a decentralized way in accordance with the partial observations of the global network state at the VUE-pairs. Numerical simulations validate the theoretical analysis and show the effectiveness of the proposed online learning algorithm. |
| Tasks | Decision Making |
| Published | 2019-06-03 |
| URL | https://arxiv.org/abs/1906.00625v1 |
| https://arxiv.org/pdf/1906.00625v1.pdf | |
| PWC | https://paperswithcode.com/paper/190600625 |
| Repo | |
| Framework | |
Founded (Auto)Epistemic Equilibrium Logic Satisfies Epistemic Splitting
| Title | Founded (Auto)Epistemic Equilibrium Logic Satisfies Epistemic Splitting |
| Authors | Jorge Fandinno |
| Abstract | In a recent line of research, two familiar concepts from logic programming semantics (unfounded sets and splitting) were extrapolated to the case of epistemic logic programs. The property of epistemic splitting provides a natural and modular way to understand programs without epistemic cycles but, surprisingly, was only fulfilled by Gelfond’s original semantics (G91), among the many proposals in the literature. On the other hand, G91 may suffer from a kind of self-supported, unfounded derivations when epistemic cycles come into play. Recently, the absence of these derivations was also formalised as a property of epistemic semantics called foundedness. Moreover, a first semantics proved to satisfy foundedness was also proposed, the so-called Founded Autoepistemic Equilibrium Logic (FAEEL). In this paper, we prove that FAEEL also satisfies the epistemic splitting property something that, together with foundedness, was not fulfilled by any other approach up to date. To prove this result, we provide an alternative characterisation of FAEEL as a combination of G91 with a simpler logic we called Founded Epistemic Equilibrium Logic (FEEL), which is somehow an extrapolation of the stable model semantics to the modal logic S5. Under consideration for acceptance in TPLP. |
| Tasks | |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.09247v2 |
| https://arxiv.org/pdf/1907.09247v2.pdf | |
| PWC | https://paperswithcode.com/paper/founded-autoepistemic-equilibrium-logic |
| Repo | |
| Framework | |
New Loss Functions for Fast Maximum Inner Product Search
| Title | New Loss Functions for Fast Maximum Inner Product Search |
| Authors | Ruiqi Guo, Quan Geng, David Simcha, Felix Chern, Sanjiv Kumar, Xiang Wu |
| Abstract | Quantization based methods are popular for solving large scale maximum inner product search problems. However, in most traditional quantization works, the objective is to minimize the reconstruction error for datapoints to be searched. In this work, we focus directly on minimizing error in inner product approximation and derive a new class of quantization loss functions. One key aspect of the new loss functions is that we weight the error term based on the value of the inner product, giving more importance to pairs of queries and datapoints whose inner products are high. We provide theoretical grounding to the new quantization loss function, which is simple, intuitive and able to work with a variety of quantization techniques, including binary quantization and product quantization. We conduct experiments on standard benchmarking datasets to demonstrate that our method using the new objective outperforms other state-of-the-art methods. |
| Tasks | Quantization |
| Published | 2019-08-27 |
| URL | https://arxiv.org/abs/1908.10396v2 |
| https://arxiv.org/pdf/1908.10396v2.pdf | |
| PWC | https://paperswithcode.com/paper/new-loss-functions-for-fast-maximum-inner |
| Repo | |
| Framework | |
Learning The Best Expert Efficiently
| Title | Learning The Best Expert Efficiently |
| Authors | Daron Anderson, Douglas J. Leith |
| Abstract | We consider online learning problems where the aim is to achieve regret which is efficient in the sense that it is the same order as the lowest regret amongst K experts. This is a substantially stronger requirement that achieving $O(\sqrt{n})$ or $O(\log n)$ regret with respect to the best expert and standard algorithms are insufficient, even in easy cases where the regrets of the available actions are very different from one another. We show that a particular lazy form of the online subgradient algorithm can be used to achieve minimal regret in a number of “easy” regimes while retaining an $O(\sqrt{n})$ worst-case regret guarantee. We also show that for certain classes of problem minimal regret strategies exist for some of the remaining “hard” regimes. |
| Tasks | |
| Published | 2019-11-11 |
| URL | https://arxiv.org/abs/1911.04307v1 |
| https://arxiv.org/pdf/1911.04307v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-the-best-expert-efficiently |
| Repo | |
| Framework | |
