Study classifies twist knots with maximal self-linking number in S^3.
problem Classifying transverse-universal knots in S^3.
method Classification of transverse twist knots with maximal self-linking number.
result Obtained an infinite family of non-transverse-universal knots.
PLN-Nets with two linear layers and parallel LN achieve universal approximation.
problem Limitations of standard neural network architectures in universal approximation.
method Introduced PLN-Nets combining two linear layers with parallel LN.
result PLN-Nets achieve universal approximation, while standard LN has limited power.
New high-order universal portfolios outperform standard ones.
problem Improving upon the Cover universal portfolio.
method Constructing higher order universal portfolios by recurrence and analyzing their properties.
result Second high-order UP outperforms standard UP under perturbation.
New method creates universal perturbations to fool neural network interpretations.
problem Vulnerability of gradient-based saliency maps to adversarial perturbations.
method Gradient-based optimization and PCA-based approach to create UPI.
result Existence and successful application of Universal Perturbation for Interpretation (UPI).
We analyze the constituents stocks of the Dow Jones Industrial Average (DJIA30) and the Standard & Poor's 100 index (S&P100) of the NYSE stock exchange market. Surprisingly, we discover the data collapse of the histograms of the DJIA30 price fluctuations and of the S&P100 price fluctuations to the universal non-paramet…
Unified framework for comparing classification metrics across different imbalance rates.
problem Differences in scale and sensitivity to class imbalance rates in classification metrics.
method Introduces outperformance standardization (OPS) function to map metrics to a common scale.
result Unified o-value metric provides clear comparison across different imbalance rates.
GCNNs gain rotation invariance with more training augmentation, making SVD-Universal more effective.
problem Improving robustness of GCNNs to adversarial attacks.
method SVD-Universal technique applied to GCNNs trained with larger rotations.
result SVD-Universal becomes more effective as GCNNs gain rotation invariance.
GNNs with random node initialization are shown to be universally expressive.
problem Limitations of standard GNNs in distinguishing graphs.
method Random node initialization (RNI) to enhance GNNs' expressive power.
result GNNs with RNI are proven to be universally expressive.
We extend a recently proposed 1-nearest-neighbor based multiclass learning algorithm and prove that our modification is universally strongly Bayes-consistent in all metric spaces admitting any such learner, making it an "optimistically universal" Bayes-consistent learner. This is the first learning algorithm known to e…
We establish blow-up profiles for any blowing-up sequence of solutions of general conformally invariant fully nonlinear elliptic equations on Euclidean domains. We prove that (i) the distance between blow-up points is bounded from below by a universal positive number, (ii) the solutions are very close to a single stand…
This work establishes universality for deep equivariant networks, overcoming limitations of previous approaches.
problem Rarity of universality results for equivariant neural networks, especially in high-dimensional settings.
method Develops a more general account of universality for equivariant networks, introducing entry-wise separability and readout layers.
result Deep equivariant networks achieve universality under entry-wise separability, with or without readout layers.
We show that there exists a transverse link in the standard contact structures on the 3-sphere such that all contact 3-manifolds are contact branched covers over this transverse link.
A fast method computes class-specific adversarial perturbations for deep networks.
problem Computing robust adversarial perturbations for deep networks.
method Linear function of weights, no training data, no hyper-parameters.
result Obtains 34% to 51% fooling rate on ImageNet, transfers across models.
New model closes gap in understanding equivariant set functions.
problem Understanding universality of equivariant set functions.
method Proves PointNet not equivariant universal and introduces PointNetST.
result PointNetST is the simplest permutation equivariant universal model.
Efficiently constructs prediction bands with minimal assumptions.
problem Uncertainty quantification for nonparametric, heteroscedastic data.
method Semi-definite programming for data-adaptive prediction bands.
result Strong non-asymptotic coverage properties with minimal distributional assumptions.
New findings on universal learning in contextual bandits with adversarial rewards.
problem Learning in contextual bandits with time-varying, adversarial rewards.
method Characterization of learnable processes and necessary/sufficient conditions for universal learning.
result Optimistic universal learning for contextual bandits with adversarial rewards is impossible in general.
Universal supervised learning is considered from an information theoretic point of view following the universal prediction approach, see Merhav and Feder (1998). We consider the standard supervised "batch" learning where prediction is done on a test sample once the entire training data is observed, and the individual s…
Study shows fine-tuned linear models outperform pretrained ones in transfer learning.
problem Transfer learning and fine-tuning in linear models for regression and binary classification.
method Stochastic gradient descent on pretrained linear models with small target data sets.
result Fine-tuned models outperform pretrained ones under certain conditions.
A new learning rule consistently reduces error over data samples.
problem Finding a learning rule that consistently reduces error over all data distributions.
method A deterministic, data-dependent partitioning rule that only partitions cyclic intervals with sufficient empirical diversity of labels.
result The expected error is monotone non-increasing with the sample size under every data distribution.
The Bayesian framework is a well-studied and successful framework for inductive reasoning, which includes hypothesis testing and confirmation, parameter estimation, sequence prediction, classification, and regression. But standard statistical guidelines for choosing the model class and prior are not always available or…
GNP models predictive correlations and outperforms NPs.
problem Training and understanding of Neural Processes.
method Proposed a new model, Gaussian Neural Process (GNP), which incorporates translation equivariance and provides universal approximation guarantees.
result Demonstrates encouraging performance and provides universal approximation guarantees.
Unified analytical tool for non-Markovian jump processes.
problem Analyzing history-dependent jump processes with non-Markovian behavior.
method Developed a standard form of master equations using Laplace-space embedding and asymptotic solution.
result Unified analytical toolset for general non-Markovian processes, leading to the GLE approximation.
A new risk budgeting scheme derived from universal portfolio theory.
problem Risk allocation in portfolio management.
method Integrates Cover's universal portfolio selection with modern risk allocation models.
result Proves mathematical equivalence to a novel universal portfolio scheme.
New algorithm achieves consistent learning from context in bandit problems.
problem Learning from context in bandit problems with non-i.i.d. contexts.
method Optimistically universal learning rule balancing generalization and personalization.
result Achieves universal consistency for large classes of non-i.i.d. contexts.
New method UADs improves transferability of adversarial perturbations.
problem Transferability of adversarial perturbations across different DNN architectures.
method Proposes Universal Adversarial Directions (UADs) to improve transferability.
result UADs can achieve a Nash equilibrium, indicating potential transferability.
We discuss when and why custom multi-factor risk models are warranted and give source code for computing some risk factors. Pension/mutual funds do not require customization but standardization. However, using standardized risk models in quant trading with much shorter holding horizons is suboptimal: 1) longer horizon …
Deep learning models converge to Gaussian dynamics with mixed structured inputs.
problem Understanding neural network dynamics with complex input distributions.
method Extended hidden manifold model to Gaussian mixtures, analyzed via SGD.
result Learning dynamics with mixed inputs converge to Gaussian behavior.
The Basilica Julia set is universally equivalent to other complex dynamics sets.
problem Establishing the universality of the Basilica Julia set.
method Quasiconformal equivalence and geometric finiteness.
result The Basilica Julia set is quasiconformally equivalent to other complex dynamics sets.
Enhances generative models by improving expressivity without high computational cost.
problem Improving expressivity in generative models without increasing computational complexity.
method Proposes a new family of generative flows on an augmented data space, proving they can approximate a Hamiltonian ODE as a universal transport map.
result Demonstrates state-of-the-art performance on flow-based generative modeling benchmarks.
Persistence diagrams from random matrices follow RMT universality, offering a new spectral diagnostic.
problem Understanding spectral properties of random matrices using topological data analysis.
method Applying Morse theory to persistence diagrams of quadratic forms restricted to unit spheres.
result Persistence entropy outperforms traditional level spacing ratios in discriminating random matrix ensembles.
This paper begins the study of relations between Riemannian geometry and global properties of contact structures on 3-manifolds. In particular we prove an analog of the sphere theorem from Riemannian geometry in the setting of contact geometry. Specifically, if a given three dimensional contact manifold (M,ξ) admits a …
New universal invariant operators are introduced in a class of geometries which include the quaternionic structures and their generalisations as well as 4-dimensional conformal (spin) geometries. It is shown that, in a broad sense, all invariants and invariant operators arise from these universal operators and that the…
This paper demonstrates the power of the calculus developed in the two previous parts of the series for all real forms of the almost Hermitian symmetric structures on smooth manifolds, including e.g. conformal Riemannian and almost quaternionic geometries. Exploiting some finite dimensional representation theory of sim…
This work initiates a general study of learning and generalization without the i.i.d. assumption, starting from first principles. While the traditional approach to statistical learning theory typically relies on standard assumptions from probability theory (e.g., i.i.d. or stationary ergodic), in this work we are inter…
Prototype rules simplify multiclass classification in metric spaces, achieving consistency and reduced complexity.
problem Multiclass classification in metric spaces, focusing on universal consistency and convergence rates.
method Novel Proto-NN and hybrid rules for multiclass classification in metric spaces, analyzing convergence rates.
result Proto-NN is universally consistent and simpler to implement, with similar computational advantages.
The study proves CR structures on specific three-manifolds are equivalent to standard structures.
problem Proving CR structures on three-manifolds are equivalent to standard structures.
method Analyzing Yamabe constant and total Q′-curvature to deduce CR equivalence. result Closed CR three-manifolds with certain curvature properties are equivalent to standard structures.
Signatures of universality are detected by comparing individual eigenvalue distributions and level spacings from financial covariance matrices to random matrix predictions. A chopping procedure is devised in order to produce a statistical ensemble of asset-price covariances from a single instance of financial data sets…
A plethora of natural, artificial and social systems exist which do not belong to the Boltzmann-Gibbs (BG) statistical-mechanical world, based on the standard additive entropy SBG and its associated exponential BG factor. Frequent behaviors in such complex systems have been shown to be closely related to q-stati…
Study on contact forms with constant curvature on CR manifolds.
problem Existence of non-homothetic contact forms with constant Tanaka-Webster scalar curvature.
method Analysis of universal covers and profinite completions of CR manifolds.
result Existence of infinitely many non-homothetic contact forms on compact CR manifolds.
The universe's shape and size are determined in general cosmological models.
problem Determining the shape and size of the universe in general cosmological models.
method Using differential geometry and extensions of the Bonnet-Myers theorem, the researchers derived conditions for a finite universe and provided a list of possible topologies.
result The spatial sections of the universe can be either S1imesS2, S1ildeimesS2, S1imesRP2, RP3#RP3, or covered by the sphere S3 or torus T3. Constructs new topological theories in 2D not fitting standard axioms.
problem Developing new topological theories in 2D that don't conform to traditional axioms.
method Universal construction by Blanchet et al., Kronecker's characterization, field extension, Hankel matrices, Schur polynomials, and foam evaluation.
result Introduction of non-multiplicative theories and classification over finite-dimensional state spaces.
We study noncompact surfaces evolving by mean curvature flow. Without any symmetry assumptions, we prove that any solution that is C3-close at some time to a standard neck will develop a neckpinch singularity in finite time, will become asymptotically rotationally symmetric in a space-time neighborhood of its singul…
The paper critiques UBI as ineffective for addressing technological unemployment.
problem Technological unemployment due to automation.
method Empirical data analysis and theoretical projections of UBI's impact.
result UBI is not an effective solution for improving living standards and employability among displaced workers.
We give necessary and sufficient conditions for a closed connected co-orientable contact 3-manifold (M,ξ) to be a standard lens space based on assumptions on the Reeb flow associated to a defining contact form. Our methods also provide rational global surfaces of section for nondegenerate Reeb flows on $(L(p,q),ξ_{…
We prove the existence of a degree 7 Vassiliev invariant of long (or string) two-component links which is not preserved under the simultaneous change of orientation of both components. The non-invertibility of this invariant can be detected by the standard weight system with values in the tensor square of the universal…
PieClam autoencodes graphs into communities, improving graph anomaly detection.
problem Graph anomaly detection and universal graph autoencoding.
method Probabilistic graph model with overlapping inclusive and exclusive communities.
result PieClam is a universal autoencoder that uniformly approximates any graph.
Analyzes the differential expansion of knot polynomials, focusing on its applicability and modifications.
problem Understanding the differential expansion of colored knot polynomials, especially for non-trivial knots and those with defects.
method Examines the current status of differential expansion, analyzes its applicability to non-trivial knots, and introduces a new transformation.
result A new transformation V that converts Z to standard Z-factors and allows for the calculation of F. ULFS-KDPE estimates parameters efficiently without influence functions.
problem Estimating pathwise differentiable parameters in nonparametric models.
method Kernel debiased plug-in estimator based on universal least favorable submodel.
result Semiparametric efficiency achieved without influence function derivation.