Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

4.2%8.3%12.5%16.7% · Sep 199519922001200920172026
48 results for movie reviews

We present a grid diagram analogue of Carter, Rieger and Saito's smooth movie theorem. Specifically, we give definitions for grid movies, grid movie isotopies and present a definition of grid planar isotopy as a particular subset of the grid diagram moves: stabilization, destabilization and commutation. We show that gr…

2013-03-07abs ↗pdf ↗

Paper classifies movie genres using multimodal data.

problem Challenging task of multi-label movie genre classification.
method Created dataset from video clips, subtitles, synopses, and posters. Extracted features using various descriptors. Evaluated using different classifiers and late fusion strategy.
result Best F-Score result of 0.628 achieved by combining LSTM on synopses and CNN on movie trailer frames.

'There is no terror in the bang, only is the anticipation of it' - Alfred Hitchcock. Yet there is everything in correctly anticipating the bang a movie would make in the box-office. Movies make a high profile, billion dollar industry and prediction of movie revenue can be very lucrative. Predicted revenues can be used …

2018-04-03abs ↗pdf ↗

We introduce supervised latent Dirichlet allocation (sLDA), a statistical model of labelled documents. The model accommodates a variety of response types. We derive an approximate maximum-likelihood procedure for parameter estimation, which relies on variational methods to handle intractable posterior expectations. Pre…

2010-03-03abs ↗pdf ↗

A shadow diagram is a knot diagram with under-over information omitted; a shadow movie is a sequence of shadow diagrams related by shadow Reidemeister moves. We show that not every shadow movie arises as the shadow of a Reidemeister movie, meaning a sequence of classical knot diagrams related by classical Reidemeister …

2011-06-17abs ↗pdf ↗

Current recommender systems exploit user and item similarities by collaborative filtering. Some advanced methods also consider the temporal evolution of item ratings as a global background process. However, all prior methods disregard the individual evolution of a user's experience level and how this is expressed in th…

2017-05-06abs ↗pdf ↗

As more and more people shift their movie watching online, competition between movie viewing websites are getting more and more intense. Therefore, it has become incredibly important to accurately predict a given user's watching list to maximize the chances of keeping the user on the platform. Recent studies have sugge…

2019-09-02abs ↗pdf ↗

Two singular links are cobordant if one can be obtained from the other by singular link isotopy together with a combination of births or deaths of simple unknotted curves, and saddle point transformations. A movie description of a singular link cobordism in 4-space is a sequence of singular link diagrams obtained from …

2015-07-15abs ↗pdf ↗

We present a marked analogue of Carter and Saito's movie theorem. Our definition of marking was chosen to coincide with the markings that arise in link Floer homology. In order to deal with complications arising from certain isotopies, we define three equivalence relations for marked surfaces and work over an equivalen…

2014-07-17abs ↗pdf ↗

In today's day and age when almost every industry has an online presence with users interacting in online marketplaces, personalized recommendations have become quite important. Traditionally, the problem of collaborative filtering has been tackled using Matrix Factorization which is linear in nature. We extend the wor…

2018-07-14abs ↗pdf ↗

The paper uses geometry to assess how hard examples are for NLP models.

problem Challenges in NLP datasets and classifiers, especially with shallow features.
method Information geometry to quantify example difficulty, exploring BERT, CNN, and fasttext.
result Deep learning models are vulnerable to word substitutions in difficult examples.

We adapt the optimization's concept of momentum to reinforcement learning. Seeing the state-action value functions as an analog to the gradients in optimization, we interpret momentum as an average of consecutive qq-functions. We derive Momentum Value Iteration (MoVI), a variation of Value Iteration that incorporates …

2019-10-21abs ↗pdf ↗

Solves the film scheduling and staggered showtimes problem for movie theaters.

problem Maximize attendance and revenue by scheduling films with staggered showtimes.
method Binary integer linear optimization to find optimal schedules for each cluster of neighboring locations.
result Optimal scheduling cannot be done for all locations at once, but must be done for each cluster.

This project explores several Machine Learning methods to predict movie genres based on plot summaries. Naive Bayes, Word2Vec+XGBoost and Recurrent Neural Networks are used for text classification, while K-binary transformation, rank method and probabilistic classification with learned probability threshold are employe…

2018-01-15abs ↗pdf ↗

Derives a Matern Gaussian process on hypergraphs for regression and embedding.

problem Regression and embedding of vertices in hypergraphs with uncertainty.
method Derives a Matern Gaussian process on hypergraphs, embeds vertices into latent space, identifies inducing vertices for scalable inference.
result Enables estimation of regression models with hypergraph structure informed correlation and uncertainty.

Supervised topic models utilize document's side information for discovering predictive low dimensional representations of documents. Existing models apply the likelihood-based estimation. In this paper, we present a general framework of max-margin supervised topic models for both continuous and categorical response var…

2009-12-30abs ↗pdf ↗

Relational probabilistic models have the challenge of aggregation, where one variable depends on a population of other variables. Consider the problem of predicting gender from movie ratings; this is challenging because the number of movies per user and users per movie can vary greatly. Surprisingly, aggregation is not…

2017-07-25abs ↗pdf ↗

Predict missing movie ratings or graph embeddings with low rank matrices.

problem Predicting missing entries in a ratings matrix or graph embeddings with known linear relations.
method Low rank matrix completion approach applied to graph embeddings.
result Effective methods for predicting missing entries in matrices and graph embeddings.

Recently, several methods have been proposed to explain the predictions of recurrent neural networks (RNNs), in particular of LSTMs. The goal of these methods is to understand the network's decisions by assigning to each input variable, e.g., a word, a relevance indicating to which extent it contributed to a particular…

2019-04-26abs ↗pdf ↗

New procedures connect braid charts, triplane diagrams, and braid movies for knotted surfaces.

problem Understanding the braid index and bridge index of knotted surfaces in 4D.
method Introducing rainbow diagrams and new procedures for passing among triplane diagrams, braid movies, and braid charts.
result Inequalities relating braid index and bridge index of 2-knots are obtained.

Much work has been done in understanding human creativity and defining measures to evaluate creativity. This is necessary mainly for the reason of having an objective and automatic way of quantifying creative artifacts. In this work, we propose a regression-based learning framework which takes into account quantitative…

2017-07-18abs ↗pdf ↗

Predicts EHR features that improve prediction, learning coherent topics.

problem Balancing prediction quality and coherence in EHR topic models.
method Prediction-focused topic model that uses supervisory signal to retain relevant features.
result Prediction-focused topic models learn more coherent topics while maintaining competitive predictions.

We present 27 problems encountered in automating the translation of movie/TV show subtitles. We categorize each problem in one of the three categories viz. problems directly related to textual translation, problems related to subtitle creation guidelines, and problems due to adaptability of machine translation (MT) eng…

2019-09-04abs ↗pdf ↗

We show that if KK is a fibered ribbon knot in S3=B4S^3=\partial B^4 bounding a ribbon disk DD, then given an extra transversality condition the fibration on S3ν(K)S^3\setminusν(K) extends to a fibration of B4ν(D)B^4\setminusν(D). This partially answers a question of Casson and Gordon. In particular, we show the fibration alway…

2018-11-23abs ↗pdf ↗

The paper extends surface link coloring theory to triplane diagrams and knots.

problem Understanding the topological properties of knots and surfaces in 4-space.
method Translated Niebrzydowski's theory of region colorings to triplane diagrams and movies of knots, providing inequalities and applications.
result Yoshikawa's 2-knots 919_1 and 10210_2 are non-invertible.

We use deep learning to model interactions across two or more sets of objects, such as user-movie ratings, protein-drug bindings, or ternary user-item-tag interactions. The canonical representation of such interactions is a matrix (or a higher-dimensional tensor) with an exchangeability property: the encoding's meaning…

2018-03-07abs ↗pdf ↗

A new method selects models for ensemble learning to maximize mutual information, outperforming existing approaches.

problem Selecting models for ensemble learning to improve performance and reduce correlation issues.
method Formulate budgeted ensemble selection as maximizing mutual information, use Gaussian-copula to model correlated errors, propose a greedy mutual-information selection algorithm.
result Our method consistently outperforms strong baselines across multiple datasets.

A new teacher-class network method compresses DNNs by distributing knowledge to multiple student networks.

problem Overwhelming size of Deep Neural Networks (DNNs).
method Single teacher with multiple student networks, transferring knowledge to each student.
result The combined knowledge of the class of students achieves better performance and reduces parameters.

Distributions over rankings are used to model data in various settings such as preference analysis and political elections. The factorial size of the space of rankings, however, typically forces one to make structural assumptions, such as smoothness, sparsity, or probabilistic independence about these underlying distri…

2012-02-14abs ↗pdf ↗