arXiv research

Proposes a method to evaluate generalizability in causal inference models.

Frengression models causal data flexibly and faithfully.

A new cost-frugal HPO method controls training cost during optimization.

New model considers varying costs in learning, outperforming existing methods.

Frugal method predicts multiple local electricity loads efficiently.

A new optimizer saves significant shots in quantum machine learning.

Frugal Flows learn complex data and infer marginal causal effects.

Spectral regularization improves learning over combinatorial spaces with limited data.

Sampling a fraction of pairs can match full evaluation in machine learning losses.

New approach selects sparse features without validation.

Model learns brevity by exposing to easy problems, improving efficiency without explicit length penalties.

We present an LDA approach to entity disambiguation. Each topic is associated with a Wikipedia article and topics generate either content words or entity mentions. Training such models is challenging because of the topic and vocabulary size, both in the millions. We tackle these problems using a novel distributed infer…

The family of temporal difference (TD) methods span a spectrum from computationally frugal linear methods like TD(λ) to data efficient least squares methods. Least square methods make the best use of available data directly computing the TD solution and thus do not require tuning a typically highly sensitive learning r…

In many real-world scenarios where data is high dimensional, test time acquisition of features is a non-trivial task due to costs associated with feature acquisition and evaluating feature value. The need for highly confident models with an extremely frugal acquisition of features can be addressed by allowing a feature…

We provide a mathematical definition of fragility and antifragility as negative or positive sensitivity to a semi-measure of dispersion and volatility (a variant of negative or positive "vega") and examine the link to nonlinear effects. We integrate model error (and biases) into the fragile or antifragile context. Unli…

The paper introduces various canonical parameterizations for 2D-curved shapes.

There are currently two parameterizations used to derive fixed kernels corresponding to infinite width neural networks, the NTK (Neural Tangent Kernel) parameterization and the naive standard parameterization. However, the extrapolation of both of these parameterizations to infinite width is problematic. The standard p…

Paper introduces SPADE method to protect classifiers from OOD and adversarial samples.

New parameterization for $(1,1)$-knots simplifies their study.

Algorithms typically come with tunable parameters that have a considerable impact on the computational resources they consume. Too often, practitioners must hand-tune the parameters, a tedious and error-prone task. A recent line of research provides algorithms that return nearly-optimal parameters from within a finite …

Stochastic parameterizations account for uncertainty in the representation of unresolved sub-grid processes by sampling from the distribution of possible sub-grid forcings. Some existing stochastic parameterizations utilize data-driven approaches to characterize uncertainty, but these approaches require significant str…

The current paper discusses some new results about conformal polynomic surface parameterizations. A new theorem is proved: Given a conformal polynomic surface parameterization of any degree it must be harmonic on each component. As a first geometrical application, every surface that admits a conformal polynomic paramet…

Polynomially parameterizes knots and spheres, proving analogous results.

Conformal surface parameterization is useful in graphics, imaging and visualization, with applications to texture mapping, atlas construction, registration, remeshing and so on. With the increasing capability in scanning and storing data, dense 3D surface meshes are common nowadays. While meshes with higher resolution …

Two novel algorithms for conformal parameterization of multiply-connected surfaces.

The paper analyzes how over-parameterization affects GD convergence in matrix sensing problems.

Novel framework for policy optimization with general parameterization and linear convergence.

We introduce a new parameterization method for deep learning layers using spectral tensor train decomposition.

Develops a method for conformal parameterization of point clouds without fixed boundaries.

Point cloud is the most fundamental representation of 3D geometric objects. Analyzing and processing point cloud surfaces is important in computer graphics and computer vision. However, most of the existing algorithms for surface analysis require connectivity information. Therefore, it is desirable to develop a mesh st…

Least squares regression shows unexpected double descent in under-parameterized models.

The paper proposes methods for volumetric parameterization of 3D solid manifolds.

This is a survey of the theory of complex projective (CP^1) structures on compact surfaces. After some preliminary discussion and definitions, we concentrate on three main topics: (1) Using the Schwarzian derivative to parameterize the moduli space (2) Thurston's parameterization of the moduli space using grafting (3) …

Study shows how over-parameterized classifiers can still perform well on noisy data.

Improves adaptivity in sequence models by over-parameterizing.

In the overview, a generic mathematical object (mapping) is introduced, and its relation to model physics parameterization is explained. Machine learning (ML) tools that can be used to emulate and/or approximate mappings are introduced. Applications of ML to emulate existing parameterizations, to develop new parameteri…

A new method finds DAG models without ground truth.

Gradient descent recovers low-rank matrices from corrupted measurements with double over-parameterization.

New method improves deep learning models robustness to label noise.

We study the pull-back of the 2-parameter family of quotient elastic metrics introduced in Mio-Srivastava-Joshi on the space of arc-length parameterized loops. This point of view has the advantage of concentrating on the manifold of arc-length parameterized curves, which is a very natural manifold when the analysis of …

Gradient descent slows significantly in over-parameterized single neuron learning.

New framework for better mapping of surfaces onto ellipsoids.

This paper explores adaptive methods in over-parameterized linear regression.

New methods solve tensor-on-tensor regression with unknown rank, revealing benefits of over-parameterization.

Local PCA detects intrinsic parameterization of complex thermo-chemical state-spaces.

Local convergence theory for mildly over-parameterized neural nets.

Small parameterized towers improve multi-task learning efficiency and generalization.

In this paper, we introduce a parameterized discrete curvature ($α$-curvature) for piecewise linear metrics on polyhedral surfaces, which is a generalization of the classical discrete curvature. A discrete uniformization theorem is established for the parameterized discrete curvature, which generalizes the discrete uni…