arXiv research

SAFER method certifies robustness to word substitutions without model structure.

The goal of homomorphic encryption is to encrypt data such that another party can operate on it without being explicitly exposed to the content of the original data. We introduce an idea for a privacy-preserving transformation on natural language data, inspired by homomorphic encryption. Our primary tool is {\em obfusc…

Defect of knot polynomials remains invariant under certain braid substitutions.

The paper introduces a method to improve adversarial robustness in neural networks using randomized perturbations.

We construct new families of non-hyperelliptic Lefschetz fibrations by applying the daisy substitutions to the families of words $(c_1c_2 \cdots c_{2g-1}c_{2g}{c_{2g+1}}^2c_{2g}c_{2g-1} \cdots c_2c_1)^2 = 1$, $(c_1c_2 \cdots c_{2g}c_{2g+1})^{2g+2} = 1$, and $(c_1c_2 \cdots c_{2g-1}c_{2g})^{2(2g+1)} = 1$ in the mapping …

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

Model learns image-word associations from captions using contrastive learning.

The paper assesses text classification robustness through maximal safe radius computation.

We combine concepts from random matrix theory and free probability together with ideas from the theory of commutator length in groups and maps from surfaces, and establish new connections between the two. More particularly, we study measures induced by free words on the unitary groups $U(n)$. Every word $w$ in the free…

Most of the parameters in large vocabulary models are used in embedding layer to map categorical features to vectors and in softmax layer for classification weights. This is a bottle-neck in memory constraint on-device training applications like federated learning and on-device inference applications like automatic spe…

Proposes BU-SPO method to improve text classification robustness.

We define 2-dimensional topological substitutions. A tiling of the Euclidean plane, or of the hyperbolic plane, is substitutive if the underlying 2-complex can be obtained by iteration of a 2-dimensional topological substitution. We prove that there is no primitive substitutive tiling of the hyperbolic plane $\mathbb{H…

A method estimates causal parameters using a latent variable recovery.

We introduce Markov substitute processes, a new model at the crossroad of statistics and formal grammars, and prove its main property : Markov substitute processes with a given support form an exponential family.

Study generalizes Lebesgue curves to new space-filling and fractal sets.

The definition of deposit substitutes in Philippine tax law fails to consider the maturity of a debt instrument. This makes it possible for long-term bonds to be considered as deposit substitutes if they meet the 20-lender rule, taxable at 20% final tax. However, long-term debt instruments cannot realistically function…

This research converts visual information into audio for users to perceive.

The study proves a theorem about subword complexity for free group automorphisms.

Since the 1970's, physicists and mathematicians who study random matrices in the GUE or GOE models are aware of intriguing connections between integrals of such random matrices and enumeration of graphs on surfaces. We establish a new aspect of this theory: for random matrices sampled from the group $\mathcal{U}\left(n…

Geometric theory explains substitutability in market outcomes based on production constraints.

New algorithm for clustering data streams with no substitutions.

We study the sample-based k-median clustering objective under a sequential setting without substitutions. In this setting, an i.i.d. sequence of examples is observed. An example can be selected as a center only immediately after it is observed, and it cannot be substituted later. The goal is to select a set of centers …

Optimized certainty equivalents (OCEs) is a family of risk measures widely used by both practitioners and academics. This is mostly due to its tractability and the fact that it encompasses important examples, including entropic risk measures and average value at risk. In this work we consider stochastic optimal control…

This paper investigates and compares currency substitution between the currencies of Central and Eastern European (CEE) countries and the euro. In addition, we develop a model with microeconomic foundations, which identifies difference between currency substitution and money demand sensitivity to exchange rate variatio…

PASS protects private attributes by stochastically substituting data.

Suppose that f and g are Markov surjections, each defined on a wedge of circles, each fixing the branch point and having the branch point as the only critical value. We show that if the points in the inverse limit spaces associated with f and g corresponding to the branch point are distinguished then these inverse limi…

Deep neural networks (DNNs) are one of the most prominent technologies of our time, as they achieve state-of-the-art performance in many machine learning tasks, including but not limited to image classification, text mining, and speech processing. However, recent research on DNNs has indicated ever-increasing concern o…

This paper explores how the generalization of substitute classifiers affects the success of black-box adversarial attacks.

Network models assume unrealistic idiosyncratic risk, which can be mitigated by allowing for correlated shocks.

Develops methods to improve demand counterfactuals from imperfect proxies.

Flexible Kernels for Protein Property Prediction

We analyze the practical consequences of the bilateral counterparty risk adjustment. We point out that past literature assumes that, at the moment of the first default, a risk-free closeout amount will be used. We argue that the legal (ISDA) documentation suggests in many points that a substitution closeout should be u…

Integrated Assessment Models (IAMs) are mainstay tools for assessing the long-term interactions between climate and the economy and for deriving optimal policy responses in the form of carbon prices. IAMs have been criticized for controversial discount rate assumptions, arbitrary climate damage functions, and the inade…

The "color" in the colored Jones polynomial is an integer parameter. In this paper, a periodic pattern of the values of the colored Jones polynomial at the second and the third roots of unity is found. If we substitute -1 to the colored Jones polynomial, the value is alternately 1 or the determinant of the given link. …

New proof shows how to fill a square with Fibonacci curve.

We present Distributed Equivalent Substitution (DES) training, a novel distributed training framework for large-scale recommender systems with dynamic sparse features. DES introduces fully synchronous training to large-scale recommendation system for the first time by reducing communication, thus making the training of…

Deep neural network (DNN) as a popular machine learning model is found to be vulnerable to adversarial attack. This attack constructs adversarial examples by adding small perturbations to the raw input, while appearing unmodified to human eyes but will be misclassified by a well-trained classifier. In this paper, we fo…

This work bounds classification error in machine learning for low Bayes error conditions.

We develop SHOPPER, a sequential probabilistic model of shopping data. SHOPPER uses interpretable components to model the forces that drive how a customer chooses products; in particular, we designed SHOPPER to capture how items interact with other items. We develop an efficient posterior inference algorithm to estimat…

The paper studies symplectic operations on Stein fillings of Brieskorn singularities.

Is the elasticity of intertemporal substitution (EIS) more or less than one? This question can be answered by confronting theoretical results of asset pricing models with investor behaviour during episodes of stock market panic. If we consider these episodes as periods of high risk aversion, then lower asset prices are…

We introduce several new families of relations in the mapping class groups of planar surfaces, each equating two products of right-handed Dehn twists. The interest of these relations lies in their geometric interpretation in terms of rational blowdowns of 4-manifolds, specifically via monodromy substitution in Lefschet…

Optimizes capital structure for life insurance companies with surplus participation.

The treatment effects of medications play a key role in guiding medical prescriptions. They are usually assessed with randomized controlled trials (RCTs), which are expensive. Recently, large-scale electronic health records (EHRs) have become available, opening up new opportunities for more cost-effective assessments. …

Separable Non-negative Matrix Factorization (SNMF) is an important method for topic modeling, where "separable" assumes every topic contains at least one anchor word, defined as a word that has non-zero probability only on that topic. SNMF focuses on the word co-occurrence patterns to reveal topics by two steps: anchor…

Most existing word embedding approaches do not distinguish the same words in different contexts, therefore ignoring their contextual meanings. As a result, the learned embeddings of these words are usually a mixture of multiple meanings. In this paper, we acknowledge multiple identities of the same word in different co…

We begin the systematic study of knot polynomials for the twist satellites of a knot, when its strand is substituted by a 2-strand twist knot. This is a generalization of cabling (torus satellites), when the substitute of the strand was a torus knot. We describe a general decomposition of satellite's colored HOMFLY in …

There are certain families of words and word sequences (words in the generators of a two-generator group) that arise frequently in the Teichm{ü}ller theory of hyperbolic three-manifolds and Kleinian and Fuchsian groups and in the discreteness problem for two generator matrix groups. We survey some of the families of su…