Single Class Universum-SVM uses additional data to improve single class learning.
problem Improving single class learning with limited positive data.
method Proposes Single Class Universum-SVM, incorporating additional data with different distribution.
result Empirical comparisons show the utility of the proposed approach.
New method learns multi-class from single-class data with confidences.
problem Learning multi-class from single-class data without additional data.
method Empirical risk minimization framework for multi-class classification.
result Method achieves Bayes-consistency with noisy confidences.
Single neurons can perform as well as dense networks in binary and multi-class recognition tasks.
problem Designing efficient neural networks for recognition tasks.
method Investigated the use of single or multiple neurons in neural networks for binary and multi-class recognition tasks.
result Sparse networks can be as efficient as dense networks in both binary and multi-class tasks.
Model reconstructs novel 3D shapes with a single prior image.
problem Generalizing single-view 3D reconstruction to new classes with limited data.
method Reframes reconstruction as refinement of a provided prior shape.
result Model reconstructs novel classes with limited training data.
We formulate a new class of conditional generative models based on probability flows. Trained with maximum likelihood, it provides efficient inference and sampling from class-conditionals or the joint distribution, and does not require a priori knowledge of the number of classes or the relationships between classes. Th…
Develops a new method for efficient stochastic bilevel optimization.
problem Stochastic bilevel optimization problems in machine learning applications.
method Single-Timescale stochAstic BiLevEl optimization (STABLE) method.
result Achieves the same order of sample complexity as stochastic gradient descent for single-level optimization.
New neural networks learn single-index models efficiently.
problem Learning low-dimensional structure in high-dimensional data.
method Shallow neural networks with frozen biases, studied via gradient flow.
result Generalization guarantees match near-optimal sample complexity.
A new classifier encodes local neighborhoods for each class using Fly Bloom Filters.
problem Efficiently classify data with single-pass learning.
method Proposes a new classifier that encodes local neighborhoods for each class with per-class Fly Bloom Filters.
result The proposed classifier's performance is competitive with nearest-neighbor classifiers and other single-pass classifiers.
Characterizes learnability of multioutput functions in various settings.
problem Learning multioutput function classes in batch and online settings.
method Characterizes learnability based on single-output restrictions.
result Complete characterization of learnability in multioutput classification and regression.
New scoring rules compare probabilistic top lists in classification.
problem Evaluation of probabilistic top lists in classification.
method Elicitability through symmetric proper scoring rules.
result Brier score provides a well-suited metric for comparison.
New method trains prototypical few-shot models on single class.
problem Train few-shot models on single class with limited examples.
method Introduce 'null class' and use batch normalization; propose Gaussian layer for distance calculation.
result Achieved high accuracy on test sets (Omniglot: 98%, MiniImageNet: 80%).
Efficiently learns Single-Index Models with constant factor approximation.
problem Learning Single-Index Models under L22 loss with unknown link functions. method An efficient algorithm using alignment sharpness for optimization.
result Achieves constant factor approximation to optimal loss for various distributions and link functions.
RL in MFGs is as hard as solving many single-agent RL problems.
problem Learning Nash Equilibrium in Mean-Field Games (MFGs).
method Introduce P-MBED to measure model complexity, develop a novel exploration strategy, and establish polynomial sample complexity results.
result Learning Nash Equilibrium in MFGs is no more statistically challenging than solving a logarithmic number of single-agent RL problems.
In contrast to conventional (single-label) classification, the setting of multilabel classification (MLC) allows an instance to belong to several classes simultaneously. Thus, instead of selecting a single class label, predictions take the form of a subset of all labels. In this paper, we study an extension of the sett…
Despite their ability to memorize large datasets, deep neural networks often achieve good generalization performance. However, the differences between the learned solutions of networks which generalize and those which do not remain unclear. Additionally, the tuning properties of single directions (defined as the activa…
We study the maximal entropy per unit generator of push-point mapping classes on the punctured disk. Our work is motivated by fluid mixing by rods in a planar domain. If a single rod moves among N-fixed obstacles, the resulting fluid diffeomorphism is in the push-point mapping class associated with the loop in π_1(D^2 …
Optimizes natural frequencies of cellular composites with various microstructures.
problem Designing cellular composites with diverse microstructures for maximizing natural frequencies.
method Data-driven topology optimization with a latent-variable Gaussian process model.
result Cellular designs with multiclass microstructures achieve higher natural frequencies.
The classical Godbillon-Vey invariant is an odd degree cohomology class that is a cobordism invariant of a single foliation. Here we investigate cohomology classes of even degree that are cobordism invariants of (germs of) 1-parameter families of foliations.
Kernel alignment measures the degree of similarity between two kernels. In this paper, inspired from kernel alignment, we propose a new Linear Discriminant Analysis (LDA) formulation, kernel alignment LDA (kaLDA). We first define two kernels, data kernel and class indicator kernel. The problem is to find a subspace to …
Study SGD dynamics in sequence models, revealing training phases and influence of sequence length.
problem Understanding SGD in sequence models like attention networks.
method Derived closed-form population loss and analyzed SGD dynamics for SSI models.
result Two distinct training phases: escape from uninformative initialization and alignment with target subspace.
The paper provides guarantees for learning switching non-linear systems from a single trajectory.
problem Learning non-linear dynamical systems with switching dynamics.
method Non-asymptotic bounds derived under stability assumptions for i.i.d. switching modes.
result Explicit convergence rates for Hölder and linear function classes based on effective sample size.
Using the theory of hyperbolic manifolds with totally geodesic boundary, we provide for every integer n greater than 1 a class of such manifolds all having Matveev complexity equal to n and Heegaard genus equal to n+1. All the elements of this class have a single boundary component of genus n, and the numbers of distin…
SGD shows distinct phases in learning single-index models, achieving optimal sample complexity and regret.
problem Learning single-index models with SGD in adaptive data settings.
method Stochastic gradient descent (SGD) with an optimal learning rate schedule.
result SGD achieves near-optimal sample complexity and regret guarantees across both burn-in and learning phases.
We prove that the deRham cohomology classes of Lee forms of locally conformally symplectic structures taming the complex structure of a compact complex surface S with first Betti number equal to 1 is either a non-empty open subset of HdR1(S,R), or a single point. In the latter case, we show that S …
New framework models uncertainty in classification debates.
problem Weak interpretability of existing uncertainty quantification methods.
method Courtroom analogy and Mixture of Dirichlet Experts (MoDEX) model.
result MoDEX achieves state-of-the-art uncertainty quantification performance.
We carry out a Painlevé analysis to find the cases where the cohomogeneity one steady Ricci soliton equation can be integrable. We concentrate on two classes of solitons: warped products and complex line bundles over a Fano Kähler Einstein base. For warped products, the analysis singles out the case with one factor whe…
A new teacher-class network method compresses DNNs by distributing knowledge to multiple student networks.
problem Overwhelming size of Deep Neural Networks (DNNs).
method Single teacher with multiple student networks, transferring knowledge to each student.
result The combined knowledge of the class of students achieves better performance and reduces parameters.
A new method for federated learning with only positive labels.
problem Learning with only positive labels leads to poor classifier performance.
method Federated Averaging with Spreadout (FedAwS) framework.
result FedAwS can almost match the performance of conventional learning with negative labels.
Methods for automated discovery of causal relationships from non-interventional data have received much attention recently. A widely used and well understood model family is given by linear acyclic causal models (recursive structural equation models). For Gaussian data both constraint-based methods (Spirtes et al., 199…
Study shows computational and statistical gaps in Gaussian Single-Index Models.
problem Statistical and computational trade-offs in high-dimensional regression problems.
method Analysis of SQ and LDP frameworks, partial-trace algorithm.
result Computational algorithms require significantly more samples than information-theoretic limits.
Estimates joint causal effects using single-variable interventions on nonlinear models.
problem Estimating joint causal effects from single-variable interventions.
method Identifiability result and practical estimator for decomposing causal effects.
result Joint effects can be inferred without joint interventional data for nonlinear additive models.
Multi-expert L2D underfits more severely, requiring new methods.
problem Underfitting in multi-expert L2D settings.
method PiCCE (Pick the Confident and Correct Expert), a surrogate-based method.
result PiCCE effectively reduces multi-expert L2D to a single-expert-like problem, resolving underfitting.
Modifying the method of [21], we compute the perturbed HF+ for some special classes of fibered three manifolds in the second highest spinc-structures Sg−2. The special classes considered in this paper include the mapping tori of Dehn twists along a single non-separating curve and along a transverse pair of c…
Improves conformal prediction by combining multiple score functions and optimizing weights.
problem Limitations of single-score conformal predictors in multi-class classification.
method Combines multiple score functions and optimizes weights to minimize prediction set size.
result Consistently outperforms single-score conformal predictors while maintaining valid coverage.
The pullback approach to global Finsler geometry is adopted. Three classes of recurrence in Finsler geometry are introduced and investigated: simple recurrence, Ricci recurrence and concircular recurrence. Each of these classes consists of four types of recurrence. The interrelationships between the different types of …
A new model explains asset returns with a single factor, improving cross-sectional performance.
problem Understanding the cross-section of asset returns with complex models.
method Proposes a non-linear single-factor asset pricing model with a nonparametric link function estimated jointly with sieve-based estimators.
result The model delivers superior cross-sectional performance with a low-dimensional approximation of the link function.
We show that on a nonorientable surface of genus at least 7 any power of a Dehn twist is equal to a single commutator in the mapping class group and the same is true, under additional assumptions, for the twist subgroup, and also for the extended mapping class group of an orientable surface of genus at least 3.
A method to generate multi-label data from single positive annotations.
problem Generating multi-label datasets is costly and impractical.
method Single-to-multi-label (S2M) sampling using Markov chain Monte Carlo.
result S2M sampling enables high-quality multi-label data with minimal annotation cost.
Generative model generates images with multiple object classes.
problem Generating images with multiple object classes.
method Conditional Deep Convolutional GAN architecture, stabilized against collapse.
result System generates diverse samples with inter-object relationships.
This paper initiates a systematic study of the relation of commensurability of surface automorphisms, or equivalently, fibered commensurability of 3-manifolds fibering over the circle. We show that every hyperbolic fibered commensurability class contains a unique minimal element, whereas the class of Seifert manifolds …
Single proxy variable helps estimate causal effects from confounders.
problem Estimating causal effects from treatment to outcome when unobserved confounders are present.
method Assumes a single, potentially multi-dimensional proxy variable of the unobserved confounder and a known mechanism generating the proxy from the confounder. Proves causal effects are identifiable under completeness assumption.
result Causal effects are identifiable under SPICE assumption.
Single-spike neurons can approximate as well as multi-spike neurons.
problem Limitation of single-spike neurons in spiking neural networks.
method Comparison of single-spike and multi-spike neural networks.
result Single-spike and multi-spike neural networks are equivalent in approximation capabilities.
New algorithms for multitask learning with long-term memory.
problem Learning from tasks partitioned into unknown segments with associated hypotheses.
method Online multitask learning algorithms exploiting segmentation and hypothesis association.
result Regret bounds and efficient algorithms for various hypothesis classes.
Paper tackles offline RL with weak assumptions on both function classes and data coverage.
problem Achieve sample-efficient offline RL with weak assumptions on both factors.
method Simple algorithm based on primal-dual formulation of MDPs, with density-ratio function modeling dual variables.
result Polynomial sample complexity achieved under realizability and single-policy concentrability.
In this paper we study the minimum dilatation pseudo-Anosov mapping classes coming from fibrations over the circle of a single 3-manifold, the mapping torus for the "simplest pseudo-Anosov braid". The dilatations that arise include the minimum dilatations for orientable mapping classes for genus g=2,3,4,5,8 as well as …
This paper shows that there are symplectic four-manifolds M with the following property: a single isotopy class of smooth embedded two-spheres in M contains infinitely many Lagrangian submanifolds, no two of which are isotopic as Lagrangian submanifolds. The examples are constructed using a special class of symplectic …
Paper proposes methods to learn with multiple incorrect labels per example.
problem Learning with a single incorrect label per example limits potential.
method Proposes a novel problem setting allowing multiple incorrect labels per example and two learning methods.
result Demonstrates improved learning with multiple incorrect labels compared to single incorrect labels.
In this paper we propose a transform method to compute the prices and greeks of barrier options driven by a class of Levy processes. We derive analytical expressions for the Laplace transforms in time of the prices and sensitivities of single barrier options in an exponential Levy model with hyper-exponential jumps. In…