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.
New algorithms reduce slate bandit regret for large slates, outperforming existing methods.
A deep reinforcement learning approach for slate re-ranking in e-commerce.
Scalable model for slate recommendation learns reward probabilities.
A new estimator reduces variance in slate bandit OPE.
This paper optimizes slate decision systems for large action spaces.
New estimator reduces risk in slate bandits by leveraging Bayes risk criterion.
Generative model learns to create coherent slates from prompts.
The conventional solution to the recommendation problem greedily ranks individual document candidates by prediction scores. However, this method fails to optimize the slate as a whole, and hence, often struggles to capture biases caused by the page layout and document interdepedencies. The slate recommendation problem …
A new recommender system uses slates and Thompson Sampling to improve diversity and click rates.
We learn hierarchical slate representations for collaborative filtering.
Efficient algorithms for contextual slate bandits with limited adaptivity.
Most practical recommender systems focus on estimating immediate user engagement without considering the long-term effects of recommendations on user behavior. Reinforcement learning (RL) methods offer the potential to optimize recommendations for long-term user engagement. However, since users are often presented with…
A new dataset tracks user interactions and click responses in online marketplaces.
New algorithms learn MNL weights efficiently for any slate size.
Ranking is a central task in machine learning and information retrieval. In this task, it is especially important to present the user with a slate of items that is appealing as a whole. This in turn requires taking into account interactions between items, since intuitively, placing an item on the slate affects the deci…
This paper studies the evaluation of policies that recommend an ordered set of items (e.g., a ranking) based on some context---a common scenario in web search, ads, and recommendation. We build on techniques from combinatorial bandits to introduce a new practical estimator that uses logged data to estimate a policy's p…
New method for evaluating sequential recommendations with lower variance.
We summarize the potential impact that the European Union's new General Data Protection Regulation will have on the routine use of machine learning algorithms. Slated to take effect as law across the EU in 2018, it will restrict automated individual decision-making (that is, algorithms that make decisions based on user…
Researchers show mixtures of ranking models are generally identifiable.
We present a deep neural-network model for lifelong learning inspired by several forms of neuroplasticity. The neural network develops continuously in response to signals from the environment. In the beginning, the network is a blank slate with no nodes at all. It develops according to four rules: (i) expansion, which …
PoPCoin aims to create a more equitable cryptocurrency.
Novel approach for large genus intersection number asymptotics.
Study laws of large numbers in online classification, determining optimal regret bounds.
Constructs non-Kähler Calabi-Yau manifolds with large Betti numbers.
Counterexamples show failure of uniform laws of large numbers for subdifferentials.
We compute the genus zero bridge numbers and give lower bounds on the genus one bridge numbers for a large class of sufficiently generic hyperbolic twisted torus knots. As a result, the bridge spectra of these knots have two gaps which can be chosen to be arbitrarily large, providing the first known examples of hyperbo…
Shows large unknotting number for simple knots.
Computing unlinking number is usually very difficult and complex problem, therefore we define BJ-unlinking number and recall Bernhard-Jablan conjecture stating that the classical unknotting/unlinking number is equal to the BJ-unlinking number. We compute BJ-unlinking number for various families of knots and links for w…
Enhances currency strategy Sharpe ratio by 30% using context-aware Learning to Rank.
New examples show clasp numbers can be zero yet four-genus can be arbitrarily large.
This note presents a kind of the strong law of large numbers for an insurance risk caused by a single catastrophic event rather than by an accumulation of independent and identically distributed risks. We derive this result by a large diversification effect resulting from optimal allocation of the risk to many reinsure…
For one can define a generalization of the unknotting number called the th untwisting number which counts the number of null-homologous twists on at most strands required to convert the knot to the unknot. We show that for any the difference between the consecutive untwisting numbers …
This paper shows how to create surface-links with many triple points.
Typically, Softmax is used in the final layer of a neural network to get a probability distribution for output classes. But the main problem with Softmax is that it is computationally expensive for large scale data sets with large number of possible outputs. To approximate class probability efficiently on such large sc…
Study finds saddle connections on random surfaces follow Poisson distribution.
The paper calculates large genus limits for quadratic differential volumes and constants.
We study the ribbon discs that arise from a symmetric union presentation of a ribbon knot. A natural notion of symmetric ribbon number is introduced and compared with the classical ribbon number. We show that the gap between these numbers can be arbitrarily large by constructing an infinite family of ribbon knots with …
We consider training probabilistic classifiers in the case of a large number of classes. The number of classes is assumed too large to perform exact normalisation over all classes. To account for this we consider a simple approach that directly approximates the likelihood. We show that this simple approach works well o…
The study finds large Betti numbers in minimal hypersurfaces with positive Ricci curvature.
We give an explicit algorithm and source code for computing optimal weights for combining a large number N of alphas. This algorithm does not cost O(N^3) or even O(N^2) operations but is much cheaper, in fact, the number of required operations scales linearly with N. We discuss how in the absence of binary or quasi-bin…
The study explores generalized divergences and exponential families with a focus on sufficient conditions and laws of large numbers.
We compare communication efficiencies of two compelling distributed machine learning approaches of split learning and federated learning. We show useful settings under which each method outperforms the other in terms of communication efficiency. We consider various practical scenarios of distributed learning setup and …
The paper calculates super Weil-Petersson volumes for large genus.
Large knots have very varied boundary slopes.
The objective of the paper is to study accuracy of multi-class classification in high-dimensional setting, where the number of classes is also large ("large , large , small " model). While this problem arises in many practical applications and many techniques have been recently developed for its solution, to t…
This paper treats the problem of screening for variables with high correlations in high dimensional data in which there can be many fewer samples than variables. We focus on threshold-based correlation screening methods for three related applications: screening for variables with large correlations within a single trea…
We study the spectrum of complete noncompact manifolds with bounded curvature and positive injectivity radius. We give general conditions which imply that their essential spectrum has an arbitrarily large finite number of gaps. In particular, for any noncompact covering of a compact manifold, there is a metric on the b…
Expectation propagation (EP) is a deterministic approximation algorithm that is often used to perform approximate Bayesian parameter learning. EP approximates the full intractable posterior distribution through a set of local approximations that are iteratively refined for each datapoint. EP can offer analytic and comp…