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.
Efficient algorithm for optimizing web page layouts in real-time.
Scalable web crawling using noisy change-indicating signals.
Optimizes web page freshness with limited crawling frequencies.
Extracts main content from web pages using neural sequence labeling.
Model predicts web page parallelism for improved browser performance and energy.
HTMLPhish detects phishing web pages using deep learning on HTML content.
A new bandit algorithm for web page item display.
Proposes intelligent web browser features for link prediction and category-wise recommendation.
Embedded markup of Web pages has seen widespread adoption throughout the past years driven by standards such as RDFa and Microdata and initiatives such as schema.org, where recent studies show an adoption by 39% of all Web pages already in 2016. While this constitutes an important information source for tasks such as W…
A search engine recommends to the user a list of web pages. The user examines this list, from the first page to the last, and clicks on all attractive pages until the user is satisfied. This behavior of the user can be described by the dependent click model (DCM). We propose DCM bandits, an online learning variant of t…
Generative models predict page quality without training, useful for low-resource settings.
Optimizes web crawling with unknown change rates using online estimation.
Malicious web content is a serious problem on the Internet today. In this paper we propose a deep learning approach to detecting malevolent web pages. While past work on web content detection has relied on syntactic parsing or on emulation of HTML and Javascript to extract features, our approach operates directly on a …
In probabilistic approaches to classification and information extraction, one typically builds a statistical model of words under the assumption that future data will exhibit the same regularities as the training data. In many data sets, however, there are scope-limited features whose predictive power is only applicabl…
A search engine usually outputs a list of web pages. The user examines this list, from the first web page to the last, and chooses the first attractive page. This model of user behavior is known as the cascade model. In this paper, we propose cascading bandits, a learning variant of the cascade model where the obje…
Descriptive titles provide crucial context for interpreting tables that are extracted from web pages and are a key component of table-based web applications. Prior approaches have attempted to produce titles by selecting existing text snippets associated with the table. These approaches, however, are limited by their d…
The web link selection problem is to select a small subset of web links from a large web link pool, and to place the selected links on a web page that can only accommodate a limited number of links, e.g., advertisements, recommendations, or news feeds. Despite the long concerned click-through rate which reflects the at…
The project aims to research on combining deep learning specifically Long-Short Memory (LSTM) and basic statistics in multiple multistep time series prediction. LSTM can dive into all the pages and learn the general trends of variation in a large scope, while the well selected medians for each page can keep the special…
We present the mixture-of-parents maximum entropy Markov model (MoP-MEMM), a class of directed graphical models extending MEMMs. The MoP-MEMM allows tractable incorporation of long-range dependencies between nodes by restricting the conditional distribution of each node to be a mixture of distributions given the parent…
Perceptual ad-blocking is vulnerable to attacks, creating new security risks.
Locality-sensitive hashing speeds up web app security testing.
DOM-Q-NET tackles web navigation by parametrizing Q functions with separate networks.
PAGE optimizes nonconvex problems with optimal convergence rates.
Optimizing an interactive system against a predefined online metric is particularly challenging, when the metric is computed from user feedback such as clicks and payments. The key challenge is the counterfactual nature: in the case of Web search, any change to a component of the search engine may result in a different…
WebGUM learns web navigation from multimodal data, outperforming previous methods.
Parallel sentences are a relatively scarce but extremely useful resource for many applications including cross-lingual retrieval and statistical machine translation. This research explores our new methodologies for mining such data from previously obtained comparable corpora. The task is highly practical since non-para…
PAGE is a simple gradient estimator for nonconvex optimization problems.
To ensure undisrupted business, large Internet companies need to closely monitor various KPIs (e.g., Page Views, number of online users, and number of orders) of its Web applications, to accurately detect anomalies and trigger timely troubleshooting/mitigation. However, anomaly detection for these seasonal KPIs with va…
Study predicts factuality and bias of news media sources.
Freya PAGE optimizes nonconvex optimization with heterogeneous, asynchronous workers.
Time-aware fact-checking improves veracity predictions for time-sensitive claims.
A nice trick for studying the billiard flow in a rational polygon is to unfold the polygon along the trajectories. This gives rise to a translation or half-translation surface tiled by the original polygon, or equivalently an Abelian or quadratic differential. Veech surfaces are a special class of translation surfaces …
Complementary products recommendation is an important problem in e-commerce. Such recommendations increase the average order price and the number of products in baskets. Complementary products are typically inferred from basket data. In this study, we propose the BB2vec model. The BB2vec model learns vector representat…
We consider the problem of classification when inputs correspond to sets of vectors. This setting occurs in many problems such as the classification of pieces of mail containing several pages, of web sites with several sections or of images that have been pre-segmented into smaller regions. We propose generalizations o…
Agent learns complex web tasks by breaking them into simpler sub-tasks.
With the growth of user-generated content, we observe the constant rise of the number of companies, such as search engines, content aggregators, etc., that operate with tremendous amounts of web content not being the services hosting it. Thus, aiming to locate the most important content and promote it to the users, the…
Investment tool predicts higher returns for Madrid real estate units.
Optimizes web publisher revenues from RTB auctions.
Alternative proof of Dynnikov's three-page index for torus links.
For many interesting tasks, such as medical diagnosis and web page classification, a learner only has access to some positively labeled examples and many unlabeled examples. Learning from this type of data requires making assumptions about the true distribution of the classes and/or the mechanism that was used to selec…
Transforms web content for better visibility in AI-driven search engines.
Efficiently projects points onto polytopes, especially useful in web-scale applications.
In this paper we show that two seemingly unrelated problems in economics, the hypothesis of integrability and the hypothesis of additive separability are linked by the absence of curvature of connections on webs naturally associated with each problem.
Study optimizes compute usage for LLM web agents, improving performance.
Estimating a large alphabet probability distribution from a limited number of samples is a fundamental problem in machine learning and statistics. A variety of estimation schemes have been proposed over the years, mostly inspired by the early work of Laplace and the seminal contribution of Good and Turing. One of the b…
The paper refines the three-page index for links, proving a new bound and characterizing specific links.
New MAB algorithm for nonstationary, semiparametric reward models.
Study the spectrum of Page's metric on complex projective spaces.