PyTorchKR Papers

최신 논문

총 1,461편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2109.14970

A Friend Recommendation System using Semantic Based KNN Algorithm

Social networking has become a major part of all our lives and we depend on it for day to day purposes. It is a medium that is used by people all around the world even in the smallest of towns. Its main purpose is to promote and aid communication between people. Social networks, such as Facebook, Twitter etc. were created for the sole purpose of helping individuals communicate about anything with each other. These networks are becoming an important and also contemporary method to make friends from any part of this world. These new friends can communicate through any form of social media. Recommendation systems exist in all the social networks which aid users to find new friends and unite to more people and form associations and alliances with people.

arXiv:2109.13687

Mechanical Normal Form of First Order State-Space Systems

In this work a state transformation is presented that transforms a given state-space system to a normal form related to mechanical systems. The underlying state-space system must meet certain requirements such that a transformation exist. If the requirements are satisfied one obtains second order differential equations which allow the application of customized and specialized algorithms.

arXiv:2109.13814공식 코드 · Papers with Code

Text2Brain: Synthesis of Brain Activation Maps from Free-form Text Query

Most neuroimaging experiments are under-powered, limited by the number of subjects and cognitive processes that an individual study can investigate. Nonetheless, over decades of research, neuroscience has accumulated an extensive wealth of results. It remains a challenge to digest this growing knowledge base and obtain new insights since existing meta-analytic tools are limited to keyword queries. In this work, we propose Text2Brain, a neural network approach for coordinate-based meta-analysis of neuroimaging studies to synthesize brain activation maps from open-ended text queries. Combining a transformer-based text encoder and a 3D image generator, Text2Brain was trained on variable-length text snippets and their corresponding activation maps sampled from 13,000 published neuroimaging studies. We demonstrate that Text2Brain can synthesize anatomically-plausible neural activation patterns from free-form textual descriptions of cognitive concepts. Text2Brain is available at https://braininterpreter.com as a web-based tool for retrieving established priors and generating new hypotheses for neuroscience research.

arXiv:2109.12378

Automaton-based Implicit Controlled Invariant Set Computation for Discrete-Time Linear Systems

In this paper, we derive closed-form expressions for implicit controlled invariant sets for discrete-time controllable linear systems with measurable disturbances. In particular, a disturbance-reactive (or disturbance feedback) controller in the form of a parameterized finite automaton is considered. We show that, for a class of automata, the robust positively invariant sets of the corresponding closed-loop systems can be expressed by a set of linear inequality constraints in the joint space of system states and controller parameters. This leads to an implicit representation of the invariant set in a lifted space. We further show how the same parameterization can be used to compute invariant sets when the disturbance is not available for measurement.

arXiv:2109.13105공식 코드 · Papers with Code

Does referent predictability affect the choice of referential form? A computational approach using masked coreference resolution

It is often posited that more predictable parts of a speaker's meaning tend to be made less explicit, for instance using shorter, less informative words. Studying these dynamics in the domain of referring expressions has proven difficult, with existing studies, both psycholinguistic and corpus-based, providing contradictory results. We test the hypothesis that speakers produce less informative referring expressions (e.g., pronouns vs. full noun phrases) when the context is more informative about the referent, using novel computational estimates of referent predictability. We obtain these estimates training an existing coreference resolution system for English on a new task, masked coreference resolution, giving us a probability distribution over referents that is conditioned on the context but not the referring expression. The resulting system retains standard coreference resolution performance while yielding a better estimate of human-derived referent predictability than previous attempts. A statistical analysis of the relationship between model output and mention form supports the hypothesis that predictability affects the form of a mention, both its morphosyntactic type and its length.

arXiv:2109.10780

Stability Assessment for Multi-Infeed Grid-Connected VSCs Modeled in the Admittance Matrix Form

The increasing use of power electronics converters to integrate renewable energy sources has been subject of concern due to the resonance oscillatory phenomena caused by their interaction with poorly damped AC networks. Early studies are focused to assess the controller influence of a single converter connected to simple networks, and they are no longer representative for existing systems. Lately, studies of multi-infeed grid-connected converters are of particular interest, and their main aim is to apply traditional criteria and identify their difficulties in the stability assessment. An extension of traditional criteria is commonly proposed as a result of these analysis, but they can be burdensome for large and complex power systems. The present work addresses this issue by proposing a simple criterion to assess the stability of large power systems with high-penetration of power converters. The criterion has its origin in the mode analysis and positive-net damping stability criteria, and it addresses the stability in the frequency domain by studying the eigenvalues magnitude and real component of dynamic models in the admittance matrix form. Its effectiveness is tested in two case studies developed in Matlab/Simulink which compare it with traditionally criteria, proving its simplicity.

arXiv:2109.09900

Estimation of the Scatterer Size Distributions in Quantitative Ultrasound Using Constrained Optimization

Quantitative ultrasound (QUS) parameters such as the effective scatterer diameter (ESD) reveal tissue properties by analyzing ultrasound backscattered echo signal. ESD can be attained through parametrizing backscatter coefficient using form factor models. However, reporting a single scatterer size cannot accurately characterize a tissue, particularly when the media contains scattering sources with a broad range of sizes. Here we estimate the probability of contribution of each scatterer size by modeling the measured form factor as a linear combination of form factors from individual sacatterer sizes. We perform the estimation using two novel techniques. In the first technique, we cast scatterer size distribution as an optimization problem, and efficiently solve it using a linear system of equations. In the second technique, we use the solution of this system of equations to constrain the optimization function, and solve the constrained problem. The methods are evaluated in simulated backscattered coefficients using Faran theory. We evaluate the robustness of the proposed techniques by adding Gaussian noise. The results show that both methods can accurately estimate the scatterer size distribution, and that the second method outperforms the first one.

arXiv:2109.09088

Relaxed Conditions for Parameterized Linear Matrix Inequality in the Form of Double Sum

The aim of this study is to investigate less conservative conditions for a parameterized linear matrix inequality (PLMI) expressed in the form of a double convex sum. This type of PLMI frequently appears in T-S fuzzy control system analysis and design problems. In this letter, we derive new, less conservative linear matrix inequalities (LMIs) for the PLMI by employing the proposed sum relaxation method based on Young's inequality. The derived LMIs are proven to be less conservative than the existing conditions related to this topic in the literature. The proposed technique is applicable to various stability analysis and control design problems for T-S fuzzy systems, which are formulated as solving the PLMIs in the form of a double convex sum. Furthermore, examples is provided to illustrate the reduced conservatism of the derived LMIs.

arXiv:2109.08939

Decentralized Governance of Stablecoins with Closed Form Valuation

We model incentive security in non-custodial stablecoins and derive conditions for participation in a stablecoin system across risk absorbers (vaults/CDPs) and holders of governance tokens. We apply option pricing theory to derive closed form solutions to the stakeholders' problems, and to value their positions within the capital structure of the stablecoin. We derive the optimal interest rate that is incentive compatible, as well as conditions for the existence of equilibria without governance attacks, and discuss implications for designing secure protocols.

arXiv:2109.08134

Comparison and Unification of Three Regularization Methods in Batch Reinforcement Learning

In batch reinforcement learning, there can be poorly explored state-action pairs resulting in poorly learned, inaccurate models and poorly performing associated policies. Various regularization methods can mitigate the problem of learning overly-complex models in Markov decision processes (MDPs), however they operate in technically and intuitively distinct ways and lack a common form in which to compare them. This paper unifies three regularization methods in a common framework -- a weighted average transition matrix. Considering regularization methods in this common form illuminates how the MDP structure and the state-action pair distribution of the batch data set influence the relative performance of regularization methods. We confirm intuitions generated from the common framework by empirical evaluation across a range of MDPs and data collection policies.

arXiv:2109.08046공식 코드 · Papers with Code

Rotation Averaging in a Split Second: A Primal-Dual Method and a Closed-Form for Cycle Graphs

A cornerstone of geometric reconstruction, rotation averaging seeks the set of absolute rotations that optimally explains a set of measured relative orientations between them. In spite of being an integral part of bundle adjustment and structure-from-motion, averaging rotations is both a non-convex and high-dimensional optimization problem. In this paper, we address it from a maximum likelihood estimation standpoint and make a twofold contribution. Firstly, we set forth a novel initialization-free primal-dual method which we show empirically to converge to the global optimum. Further, we derive what is to our knowledge, the first optimal closed-form solution for rotation averaging in cycle graphs and contextualize this result within spectral graph theory. Our proposed methods achieve a significant gain both in precision and performance.

arXiv:2109.06441공식 코드 · Papers with Code

Structure-Enhanced Pop Music Generation via Harmony-Aware Learning

Pop music generation has always been an attractive topic for both musicians and scientists for a long time. However, automatically composing pop music with a satisfactory structure is still a challenging issue. In this paper, we propose to leverage harmony-aware learning for structure-enhanced pop music generation. On the one hand, one of the participants of harmony, chord, represents the harmonic set of multiple notes, which is integrated closely with the spatial structure of music, the texture. On the other hand, the other participant of harmony, chord progression, usually accompanies the development of the music, which promotes the temporal structure of music, the form. Moreover, when chords evolve into chord progression, the texture and form can be bridged by the harmony naturally, which contributes to the joint learning of the two structures. Furthermore, we propose the Harmony-Aware Hierarchical Music Transformer (HAT), which can exploit the structure adaptively from the music, and make the musical tokens interact hierarchically to enhance the structure in multi-level musical elements. Experimental results reveal that compared to the existing methods, HAT owns a much better understanding of the structure and it can also improve the quality of generated music, especially in the form and texture.

arXiv:2109.05431

A note on closed-form spread option valuation under log-normal models

In the papers Carmona and Durrleman [7] and Bjerksund and Stensland [1], closed form approximations for spread call option prices were studied under the log normal models. In this paper, we give an alternative closed form formula for the price of spread call options under the log-normal models also. Our formula can be seen as a generalization of the closed-form formula presented in Bjerksund and Stensland [1] as their formula can be obtained by selecting special parameter values to our formula. Numerical tests show that our formula performs better for certain range of model parameters than the closed-form formula presented in Bjerksund and Stensland [1].

arXiv:2109.05535공식 코드 · Papers with Code

Adversarial Representation Learning With Closed-Form Solvers

Adversarial representation learning aims to learn data representations for a target task while removing unwanted sensitive information at the same time. Existing methods learn model parameters iteratively through stochastic gradient descent-ascent, which is often unstable and unreliable in practice. To overcome this challenge, we adopt closed-form solvers for the adversary and target task. We model them as kernel ridge regressors and analytically determine an upper-bound on the optimal dimensionality of representation. Our solution, dubbed OptNet-ARL, reduces to a stable one one-shot optimization problem that can be solved reliably and efficiently. OptNet-ARL can be easily generalized to the case of multiple target tasks and sensitive attributes. Numerical experiments, on both small and large scale datasets, show that, from an optimization perspective, OptNet-ARL is stable and exhibits three to five times faster convergence. Performance wise, when the target and sensitive attributes are dependent, OptNet-ARL learns representations that offer a better trade-off front between (a) utility and bias for fair classification and (b) utility and privacy by mitigating leakage of private information than existing solutions.

arXiv:2109.05280공식 코드 · Papers with Code

Learning To Describe Player Form in The MLB

Major League Baseball (MLB) has a storied history of using statistics to better understand and discuss the game of baseball, with an entire discipline of statistics dedicated to the craft, known as sabermetrics. At their core, all sabermetrics seek to quantify some aspect of the game, often a specific aspect of a player's skill set - such as a batter's ability to drive in runs (RBI) or a pitcher's ability to keep batters from reaching base (WHIP). While useful, such statistics are fundamentally limited by the fact that they are derived from an account of what happened on the field, not how it happened. As a first step towards alleviating this shortcoming, we present a novel, contrastive learning-based framework for describing player form in the MLB. We use form to refer to the way in which a player has impacted the course of play in their recent appearances. Concretely, a player's form is described by a 72-dimensional vector. By comparing clusters of players resulting from our form representations and those resulting from traditional abermetrics, we demonstrate that our form representations contain information about how players impact the course of play, not present in traditional, publicly available statistics. We believe these embeddings could be utilized to predict both in-game and game-level events, such as the result of an at-bat or the winner of a game.

arXiv:2109.05523

Constructing Phrase-level Semantic Labels to Form Multi-Grained Supervision for Image-Text Retrieval

Existing research for image text retrieval mainly relies on sentence-level supervision to distinguish matched and mismatched sentences for a query image. However, semantic mismatch between an image and sentences usually happens in finer grain, i.e., phrase level. In this paper, we explore to introduce additional phrase-level supervision for the better identification of mismatched units in the text. In practice, multi-grained semantic labels are automatically constructed for a query image in both sentence-level and phrase-level. We construct text scene graphs for the matched sentences and extract entities and triples as the phrase-level labels. In order to integrate both supervision of sentence-level and phrase-level, we propose Semantic Structure Aware Multimodal Transformer (SSAMT) for multi-modal representation learning. Inside the SSAMT, we utilize different kinds of attention mechanisms to enforce interactions of multi-grain semantic units in both sides of vision and language. For the training, we propose multi-scale matching losses from both global and local perspectives, and penalize mismatched phrases. Experimental results on MS-COCO and Flickr30K show the effectiveness of our approach compared to some state-of-the-art models.

arXiv:2109.04913

Adjoint Differentiation for generic matrix functions

We derive a formula for the adjoint $\overline{A}$ of a square-matrix operation of the form $C=f(A)$, where $f$ is holomorphic in the neighborhood of each eigenvalue. We then apply the formula to derive closed-form expressions in particular cases of interest such as the case when we have a spectral decomposition $A=UDU^{-1}$, the spectrum cut-off $C=A_+$ and the Nearest Correlation Matrix routine. Finally, we explain how to simplify the computation of adjoints for regularized linear regression coefficients.

arXiv:2109.04313

Continuous Event-Line Constraint for Closed-Form Velocity Initialization

Event cameras trigger events asynchronously and independently upon a sufficient change of the logarithmic brightness level. The neuromorphic sensor has several advantages over standard cameras including low latency, absence of motion blur, and high dynamic range. Event cameras are particularly well suited to sense motion dynamics in agile scenarios. We propose the continuous event-line constraint, which relies on a constant-velocity motion assumption as well as trifocal tensor geometry in order to express a relationship between line observations given by event clusters as well as first-order camera dynamics. Our core result is a closed-form solver for up-to-scale linear camera velocity {with known angular velocity}. Nonlinear optimization is adopted to improve the performance of the algorithm. The feasibility of the approach is demonstrated through a careful analysis on both simulated and real data.

arXiv:2109.03754공식 코드 · Papers with Code

Memory and Knowledge Augmented Language Models for Inferring Salience in Long-Form Stories

Measuring event salience is essential in the understanding of stories. This paper takes a recent unsupervised method for salience detection derived from Barthes Cardinal Functions and theories of surprise and applies it to longer narrative forms. We improve the standard transformer language model by incorporating an external knowledgebase (derived from Retrieval Augmented Generation) and adding a memory mechanism to enhance performance on longer works. We use a novel approach to derive salience annotation using chapter-aligned summaries from the Shmoop corpus for classic literary works. Our evaluation against this data demonstrates that our salience detection model improves performance over and above a non-knowledgebase and memory augmented language model, both of which are crucial to this improvement.

arXiv:2109.02872

Moment Matching Method for Pricing Spread Options with Mean-Variance Mixture Lévy Motions

The paper Borovkova et al. [4] uses moment matching method to obtain closed form formulas for spread and basket call option prices under log normal models. In this note, we also use moment matching method to obtain semi-closed form formulas for the price of spread options under exponential L\'evy models with mean-variance mixture. Unlike the semi-closed form formulas in Caldana and Fusai [5], where spread prices were expressed by using Fourier inversion formula for general price dynamics, our formula expresses spread prices in terms of the mixing distribution. Numerical tests show that our formulas give accurate spread prices also