New rules found to fool deep neural networks in text classification.
problem Vulnerabilities of deep neural networks in text classification.
method Coevolutionary optimization algorithm to create imperceptible adversarial samples.
result Universal rules for fooling deep neural networks in text classification exist and are sample and method agnostic.
Solves open problem on universally consistent online learning with unbounded losses.
problem Open problem on universally consistent online learning with unbounded losses.
method Constructs random measurable partitions of the instance space.
result Simple memorization rule is optimistically universal for any unbounded loss.
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.
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.
New rule universally consistent for online learning with non-ergodic data.
problem Online learning with non-ergodic data processes.
method Developed an online learning rule for processes on (X,Y) pairs.
result Generalizes past results to non-ergodic processes on (X,Y).
Consistency of k-NN rule proven in sigma-finite dimensional metric spaces.
problem Proving consistency of k-NN rule in metric spaces.
method Direct proof using Stone's theorem, investigating metric properties.
result Universal consistency of k-NN rule in sigma-finite dimensional metric spaces.
Novel approach to universal online learning for bounded losses, closing open problems.
problem Characterizing processes for universal online learning under non-i.i.d. conditions.
method Characterization of processes admitting strong and weak universal learning, introduction of optimistically universal learning rule.
result Introduction of a novel 1NN algorithm that is optimistically universal for bounded losses.
Algorithm maximizes wealth from best pairs rebalancing rule in hindsight.
problem Maximizing wealth from best pairs rebalancing rule in hindsight.
method Extends Ordentlich and Cover's max-min universal portfolio to achieve a percentage of the hindsight-optimized wealth.
result Achieves a compound-annual growth rate arbitrarily close to the best pairs rebalancing rule in hindsight.
Learning rule consistency tied to non-existence of real-valued measurable cardinals.
problem Consistency of k-NN learning rule in metric spaces.
method Analyzing separable subspaces and density conditions.
result The k-NN classifier's consistency depends on the absence of real-valued measurable cardinals.
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…
We prove the statistical consistency of kernel Partial Least Squares Regression applied to a bounded regression learning problem on a reproducing kernel Hilbert space. Partial Least Squares stands out of well-known classical approaches as e.g. Ridge Regression or Principal Components Regression, as it is not defined as…
OptiNet achieves near-minimax error rates with compression in Euclidean space.
problem Error and compression rates in non-parametric multiclass classification.
method Compression-based learning rule OptiNet and a novel general compression scheme.
result OptiNet achieves non-trivial compression rates with near-minimax error rates in Euclidean space.
New algorithms for regression with adversarial responses on various metric spaces.
problem Regression with adversarial responses under non-i.i.d. sequences.
method Proves universal consistency for a wide range of non-stationary processes.
result Achieves universal consistency for a broader class of sequences than stationary processes.
Study presents a method to induce a generalized neural network from joint group invariant functions.
problem Encoding rule of neural network internal data representation.
method Systematic method using joint group invariant function on data-parameter domain.
result Induces a generalized neural network and its inverse operator (ridgelet transform).
New concept of proper-calibeating extends classic calibrated forecasts to proper scoring rules.
problem Defining and extending calibrated forecasts to proper scoring rules.
method Extending the concepts of calibrated and calibeating forecasts to proper scoring rules and proving their properties.
result Proper-calibration always implies calibration, but proper-calibeating does not necessarily imply calibeating.
Neural operators learn to solve LQ MFGs efficiently in infinite dimensions.
problem Solving many related LQ MFG problems in infinite-dimensional settings.
method Training neural operators to map problem data to equilibrium strategies.
result NOs reliably solve unseen LQ MFG variants with controlled parameters.
Defines a universal state sum construction for various TQFTs.
problem No specific problem stated; universal construction for TQFTs.
method Defines a universal state sum construction using n-categories with specific conditions.
result Produces state sums from n-categories and handle decompositions of n+1-manifolds.
Differentially-private Bayes consistency rule for binary classification and density estimation.
problem Privacy constraints limit private learning in the distribution-free PAC model.
method Constructs a universally Bayes consistent learning rule that satisfies differential privacy.
result Private learning is possible for arbitrary distributions, even with a single algorithm.
Optimal Volt/VAR control rules are designed using deep neural networks.
problem Designing optimal Volt/VAR control rules for distributed energy resources (DERs).
method Formulate optimal rule design as a bilevel program, then reformulate it as training a deep neural network (DNN). Use proximal gradient descent (PGD) iterations to emulate Volt/VAR dynamics.
result The proposed solution can be adapted to single/multi-phase feeders and achieves enhanced steady-state voltage profiles.
This paper prices and replicates the best continuously-rebalanced portfolio in hindsight.
problem Deriving the price of a financial derivative based on the best continuously-rebalanced portfolio in hindsight.
method Analyzing the best continuously-rebalanced portfolio in hindsight for a single-stock Black-Scholes market and a general market with correlated stocks.
result The replicating strategy compounds wealth at the same asymptotic rate as the best levered rebalancing rule in hindsight, beating the market asymptotically.
New approach tackles decision-making under predictions that shape outcomes.
problem Challenges in learning optimal decision rules when predictions influence outcomes.
method Introduces performative omniprediction, a predictor that encodes optimal decision rules for multiple objectives.
result Efficient performative omnipredictors exist under a natural restriction of outcome performativity.
Paper introduces MRCs that minimize worst-case 0-1 loss, providing tight performance guarantees.
problem Minimizing worst-case 0-1 loss in classification.
method MRCs that minimize worst-case 0-1 loss with uncertainty sets of distributions.
result MRCs provide tight performance guarantees and are strongly universally consistent.
We prove trace identities for commutators of operators, which are used to derive sum rules and sharp universal bounds for the eigenvalues of periodic Schroedinger operators and Schroedinger operators on immersed manifolds. In particular, we prove bounds on the eigenvalue lambda_{N+1} in terms of the lower spectrum, bou…
This work proposes optimal decision rules for hierarchical classifiers to better align with evaluation metrics.
problem Heuristic decision rules in hierarchical classification do not align with evaluation metrics.
method Derives optimal decision rules for various prediction settings, focusing on hierarchical hFβ scores. result Optimal decision rules enhance the performance and reliability of hierarchical classifiers.
The paper proves generalization bounds and stopping rules for self-selected data in reciprocal learning.
problem Generalization of learning algorithms using self-selected data.
method Proves universal generalization bounds using covering numbers and Wasserstein ambiguity sets.
result Provides stopping rules for reciprocal learning algorithms to ensure out-of-sample performance.
In this work we show that, using the eigen-decomposition of the adjacency matrix, we can consistently estimate feature maps for latent position graphs with positive definite link function κ, provided that the latent positions are i.i.d. from some distribution F. We then consider the exploitation task of vertex classi…
Study uses logistic regression and association rules to identify early symptoms of malignant mesothelioma.
problem Difficult diagnosis of malignant mesothelioma leading to late-stage detection and poor patient survival.
method Implemented logistic regression and developed association rules to identify early symptoms.
result Categorical logistic regression improved training accuracy from 72.30% to 81.40%.
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 …
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.
Cover's celebrated theorem states that the long run yield of a properly chosen "universal" portfolio is as good as the long run yield of the best retrospectively chosen constant rebalanced portfolio. The "universality" pertains to the fact that this result is model-free, i.e., not dependent on an underlying stochastic …
A universal rule-based self-learning approach using deep reinforcement learning (DRL) is proposed for the first time to solve nonlinear ordinary differential equations and partial differential equations. The solver consists of a deep neural network-structured actor that outputs candidate solutions, and a critic derived…
We optimize rebalancing options by limiting asset allocations to a few choices, reducing the price and guaranteeing near-optimal performance.
problem Optimizing rebalancing strategies under discrete hindsight optimization.
method Restricting the set of rebalancing rules to a small number of asset allocations.
result Guaranteed near-optimal performance with a rock-bottom option price.
Course on neural networks for scientists and engineers.
problem Understanding neural networks for various applications.
method Explains neural networks through Hopfield networks, supervised learning, and unsupervised learning.
result Introduction to neural networks and their applications.
Develops optimal decision-making framework for uncertain counterfactuals.
problem Ensuring reliability of predictions in high-stakes decisions.
method Policy-Coupled Risk-Averse Conformal Prediction (PC-RACP).
result Optimal prediction sets for counterfactual decisions with valid coverage.
We present a universal algorithm for online trading in Stock Market which performs asymptotically at least as good as any stationary trading strategy that computes the investment at each step using a fixed function of the side information that belongs to a given RKHS (Reproducing Kernel Hilbert Space). Using a universa…
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. Parity functors assign labels to knot diagrams based on crossing parity.
problem Assigning consistent labels to knot diagrams.
method Define parity functors for knot diagrams and surfaces.
result Universal oriented parity functors for free knots and fixed surface knots.
Paper develops a privacy-preserving nonparametric regression method.
problem Nonparametric regression with local differential privacy constraints.
method Privatised discretisation and Laplace noise applied to feature vectors and responses.
result Strongly universally consistent estimator for regression and classification.
Diversified risk parity strategies outperform equally-weighted portfolios in various asset universes.
problem Finding optimal portfolio allocations that balance risk and reward.
method Integrates various reward-risk measures and generic allocation rules into diversified risk parity.
result Diversified reward-risk parity strategies exhibit higher average returns, Sharpe ratios, and Calmar ratios compared to equally-weighted risk portfolios.
We consider knot theories possessing a {\em parity}: each crossing is decreed {\em odd} or {\em even} according to some universal rule. If this rule satisfies some simple axioms concerning the behaviour under Reidemeister moves, this leads to a possibility of constructing new invariants and proving minimality and non-t…
Study on 1-Uryson width of polyhedra and their covers.
problem Existence of Riemannian polyhedra with bounded 1-Uryson width of covers but unbounded in the polyhedron itself.
method Investigated specific cases of virtually cyclic fundamental groups and Riemannian surfaces, showing bounds on 1-Uryson width.
result For compact polyhedra with virtually cyclic fundamental groups, 1-Uryson width of polyhedron is bounded by that of its universal cover.
Combines k-NN and RVM for improved classification accuracy.
problem Improving k-NN's performance by considering relevancy.
method Integrates k-NN and RVM in kernel space, introduces a new stopping parameter.
result Significantly prunes irrelevant attributes and improves classification accuracy.
Defines a similarity measure for classification distributions.
problem Measuring similarity between classification distributions.
method Proposes task similarity, a novel measure quantifying performance of source distributions on target distributions.
result Empirical task similarity correlates with transfer efficiency and semantic similarity of source distributions.
In this work we show that, using the eigen-decomposition of the adjacency matrix, we can consistently estimate latent positions for random dot product graphs provided the latent positions are i.i.d. from some distribution. If class labels are observed for a number of vertices tending to infinity, then we show that the …
This paper studies a continuous-time market where an agent, having specified an investment horizon and a targeted terminal mean return, seeks to minimize the variance of the return. The optimal portfolio of such a problem is called mean-variance efficient à la Markowitz. It is shown that, when the market coefficients a…
The cellular tree classifier model addresses a fundamental problem in the design of classifiers for a parallel or distributed computing world: Given a data set, is it sufficient to apply a majority rule for classification, or shall one split the data into two or more parts and send each part to a potentially different …
A new neural network framework ADNN improves financial feature construction.
problem Constructing highly informative financial features.
method Neural network (ADNN) with domain knowledge, pre-training, and data augmentation.
result ADNN produces more diversified and informative features than genetic programming.
A new neural network model identifies hysteresis universally.
problem Inability of existing models to simulate hysteresis universally.
method Inspired by the Preisach model, an Extended Preisach Neural Network (EPNN) is introduced with two hidden layers and a hybrid training algorithm.
result EPNN successfully identifies various hysteresis phenomena from different fields.