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

50101151201 · Jun 202019922001200920172026
48 results for classifier copying

We study model-agnostic copies of machine learning classifiers. We develop the theory behind the problem of copying, highlighting its differences with that of learning, and propose a framework to copy the functionality of any classifier using no prior knowledge of its parameters or training data distribution. We identi…

2019-03-05abs ↗pdf ↗

Classifies 3-manifolds with uniformly positive scalar curvature.

problem Classifying 3-manifolds with uniformly positive scalar curvature.
method Analyzes properties of 3-manifolds with mean convex boundaries and uniformly positive scalar curvature.
result 3-manifolds with uniformly positive scalar curvature are homeomorphic to sums of spherical 3-manifolds and S1imesS2\mathbb{S}^1 imes \mathbb{S}^2.

This paper classifies expanding attractors and non-transitive Anosov flows on specific knot and manifold spaces.

problem Classifying expanding attractors and non-transitive Anosov flows on specific knot and manifold spaces.
method Using the derived Anosov (DA) expanding attractor and the Franks-Williams manifold, the paper proves the uniqueness of these structures.
result The DA expanding attractor and the Franks-Williams non-transitive Anosov flow are the unique structures supported by N0N_0 and M0M_0 respectively.

We show that closed, connected 4-manifolds up to connected sum with copies of the complex projective plane are classified in terms of the fundamental group, the orientation character and an extension class involving the second homotopy group. For fundamental groups that are torsion free or have one end, we reduce this …

2018-02-27abs ↗pdf ↗

The study characterizes 3D manifolds using specific Morse-Bott functions.

problem Characterizing 3D manifolds represented as connected sums of Lens spaces, S2imesS1S^2 imes S^1, and torus bundles.
method Using Morse-Bott functions to classify the manifolds.
result Explicit characterization of the manifolds via certain Morse-Bott functions.

This paper introduces DPI, a new metric to assess data-copying risk in tabular data.

problem Measuring privacy risk of data-copying in tabular generative models.
method Proposes Data Plagiarism Index (DPI) for evaluating data-copying risk.
result DPI identifies data-copying threats to tabular data models, highlighting privacy and fairness issues.

New seq2seq model can copy entire spans, outperforming simpler models in editing tasks.

problem Editing documents or source code using seq2seq models with explicit token copying.
method Extended seq2seq model capable of copying entire input spans to output in one step, new training and inference methods.
result New model consistently outperforms simpler baselines in editing tasks of natural language and source code.

Paper analyzes gradient descent with noisy data copies for linear regression, showing regularization and acceleration effects.

problem Improving generalization in machine learning through data augmentation with noise.
method Gradient descent with on-line noisy copies for linear regression analysis.
result Training with on-line noisy copies is equivalent to ridge regularization with a specific regularization parameter.

In many real-world systems, information can be transmitted in two qualitatively different ways: by copying or by transformation. Copying occurs when messages are transmitted without modification, e.g., when an offspring receives an unaltered copy of a gene from its parent. Transformation occurs when messages are modifi…

2019-03-21abs ↗pdf ↗

We classify closed, topological spin+^+ 4-manifolds with fundamental group ππ of cohomological dimension 3\leq 3 (up to s-cobordism), after stabilization by connected sum with at most b3(π)b_3(π) copies of S2×S2S^2\times S^2. In general we must also assume that ππ also satisfies certain K-theory and assembly map conditio…

2014-11-20abs ↗pdf ↗

Study stable equivalence relations on 4-manifolds, proving homotopy equivalent manifolds with abelian fundamental group are stably diffeomorphic.

problem Classifying stable equivalence relations on 4-manifolds.
method Combination of modified and classical surgery, focusing on homotopy equivalence up to stabilisation.
result Closed oriented homotopy equivalent 4-manifolds with abelian fundamental group are stably diffeomorphic.

Shapes can roll downhill following any curve, but often return to initial orientation after crossing multiple copies.

problem How to design shapes that roll downhill along a given curve and its translations.
method Analyzing the geometric properties and motion of shapes on inclined planes.
result Most curves allow shapes to roll downhill following them and their translations, but some require crossing multiple copies.

Every lens space has a locally flat embedding in a connected sum of 8 copies of the complex projective plane and a smooth embedding in n copies of the complex projective plane for some positive integer n. We show that there is no n such that every lens space smoothly embeds in n copies of the complex projective plane.

2019-03-04abs ↗pdf ↗

GMC benchmark isolates retrieval in Transformers, revealing max-margin alignment.

problem Understanding how Transformers develop match-and-copy behavior on natural data.
method Introducing Gaussian Match-and-Copy (GMC) as a minimalist benchmark.
result Gradient descent drives parameters to diverge while aligning with max-margin separator.

Bayesian theory explains abrupt emergence of copy subcircuit in attention.

problem Understanding the abrupt emergence of the copy subcircuit in attention during training.
method Deriving a closed-form posterior over the attention matrix and reducing it to a low-dimensional order parameter space.
result Derive a phase transition in the amount of training data.

Under-parameterized networks can either copy or average teacher weights, leading to universal optimal solutions.

problem Approximating a teacher network with an under-parameterized student network.
method Analyzing shallow neural networks with erf activation function and unitary teacher weights, proving copy-average configurations are critical points and finding the optimal solution.
result The optimal solution for under-parameterized networks has a universal structure, whether copying or averaging teacher neurons.

When concept drift is detected during classification in a data stream, a common remedy is to retrain a framework's classifier. However, this loses useful information if the classifier has learnt the current concept well, and this concept will recur again in the future. Some frameworks retain and reuse classifiers, but …

2019-05-21abs ↗pdf ↗

Study shows kk-NN classifier is not universally consistent on (0,1)(0,1) but consistent on discrete and specific measure spaces.

problem Consistency of kk-NN classifier under Wasserstein distance on measure spaces.
method Analysis of kk-NN classifier properties under Wasserstein distance, use of σσ-finite metric dimension, geodesic structures of Wasserstein spaces.
result Consistency of kk-NN classifier on specific measure spaces (discrete, Gaussian, wavelet series) but not on (0,1)(0,1).

Automatic question generation is an important problem in natural language processing. In this paper we propose a novel adaptive copying recurrent neural network model to tackle the problem of question generation from sentences and paragraphs. The proposed model adds a copying mechanism component onto a bidirectional LS…

2019-09-17abs ↗pdf ↗

Parabolic geometric flows are smoothing for short time however, over long time, singularities are typically unavoidable, can be very nasty and may be impossible to classify. The idea of [CM6] and here is that, by bringing in the dynamical properties of the flow, we obtain also smoothing for large time for generic initi…

2018-09-10abs ↗pdf ↗

The paper introduces a new method to improve model generalization by routing model copies through permutations.

problem Improving model generalization in machine learning.
method The method replicates a model \(M\) times and rewire the contexts in which local learning messages are computed using permutations.
result The method improves generalization by structured message sharing rather than coupling parameters.

RBMs learn archetypes when trained on blurred copies of them, revealing a critical sample size.

problem Determining the critical sample size for RBMs to learn archetypes.
method Formal equivalence between RBMs and Hopfield networks, statistical-mechanics of disordered systems, Monte Carlo simulations.
result A phase diagram highlights regions where learning can be accomplished.

Let (X,Y)(X,Y) be a random variable consisting of an observed feature vector XXX\in \mathcal{X} and an unobserved class label Y{1,2,...,L}Y\in \{1,2,...,L\} with unknown joint distribution. In addition, let D\mathcal{D} be a training data set consisting of nn completely observed independent copies of (X,Y)(X,Y). Usual classification…

2008-01-18abs ↗pdf ↗

We prove that an odd pretzel knot is doubly slice if it has 2n+12n+1 twist parameters consisting of n+1n+1 copies of aa and nn copies of a-a for some odd integer aa. Combined with the work of Issa and McCoy, it follows that these are the only doubly slice odd pretzel knots.

2019-04-29abs ↗pdf ↗

Is it possible to generally construct a dynamical system to simulate a black system without recovering the equations of motion of the latter? Here we show that this goal can be approached by a learning machine. Trained by a set of input-output responses or a segment of time series of a black system, a learning machine …

2017-07-24abs ↗pdf ↗

A free action of the direct product of two copies of the symmetric group on 3 elements on the cartesian product of two copies of the 3-sphere is constructed. This nonlinear action is constructed using surgery. The action provides a counterexample to a conjecture of Lewis made in 1968.

1998-06-06abs ↗pdf ↗

Optimal adversarial attacks minimize mutual information, revealing classifier vulnerabilities.

problem Designing optimal attacks to degrade machine learning performance.
method Information-theoretic approach to finding optimal perturbations.
result Optimal attacks minimize mutual information between degraded and original signals.

For a closed 4-manifold X and closed 3-manifold M we investigate the smallest integer n (perhaps infinity) such that M embeds in the connected sum of n copies of X. It is proven that any lens space (or homology lens space) embeds topologically locally flatly in a connected sum of 8 copies of the complex projective plan…

2001-12-21abs ↗pdf ↗

A fibration of Rn{\mathbb R}^n by oriented copies of Rp{\mathbb R}^p is called skew if no two fibers intersect nor contain parallel directions. Conditions on pp and nn for the existence of such a fibration were given by Ovsienko and Tabachnikov. A classification of smooth fibrations of R3{\mathbb R}^3 by skew oriente…

2014-12-29abs ↗pdf ↗