Learning linear predictors with the logistic loss---both in stochastic and online settings---is a fundamental task in machine learning and statistics, with direct connections to classification and boosting. Existing "fast rates" for this setting exhibit exponential dependence on the predictor norm, and Hazan et al. (20…
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.
168,657 papers · 148 categories
Trend · papers per month
48 results for “improper predictors”
We study the question of learning an adversarially robust predictor. We show that any hypothesis class with finite VC dimension is robustly PAC learnable with an improper learning rule. The requirement of being improper is necessary as we exhibit examples of hypothesis classes with finite VC…
Study shows improper learning can outperform proper learning in misspecified models.
problem Misspecification in probabilistic prediction models.
method Investigates the performance of proper and improper learning strategies in misspecified models.
result Improper learning can achieve lower regret compared to proper learning, especially in high-dimensional settings.
Overparameterized MLR fits hyper-curves, improving model robustness.
problem Improper predictors degrade model generalizability.
method Parameterizing with a scalar and monomial basis, fitting hyper-curves.
result Hyper-curve approach yields robust predictions for noisy data.
Online Learning with Simple Predictors and a Combinatorial Characterization of Minimax in 0/1 Gamescs.LG
New bounds show simple predictors can learn complex concepts online.
problem When can simple predictors learn complex concepts in online learning?
method Characterized optimal mistake bounds for online learning with simple predictors.
result Achieved nearly optimal mistake bounds for online learning using sparse majority-vote of proper predictors.
The study classifies singularities in discrete improper affine spheres.
problem Classifying singularities in discrete improper affine spheres.
method Analysis of discrete improper affine spheres based on asymptotic nets, distinguishing singular edges and vertices.
result First step in classifying singularities of discrete nets.
In this paper we consider convex improper affine maps of the 3-dimensional affine space and classify their singularities. The main tool developed is a generating family with properties that closely resembles the area function for non-convex improper affine maps.
The paper generalizes offset Rademacher complexities to convex and non-convex problems.
problem Improper learning and convexity in statistical learning.
method Generalization of offset Rademacher complexities to convex and non-convex problems.
result The offset complexity provides versatile analytic tools for both convex and non-convex learning.
We construct a new representation formula for indefinite improper affine spheres in terms of two para-holomorphic functions and study singularities which appear in this representation formula. As a result, it follows that cuspidal cross caps never appear as the singularities on indefinite improper affine spheres and so…
Given a pair of planar curves, one can define its generalized area distance, a concept that generalizes the area distance of a single curve. In this paper, we show that the generalized area distance of a pair of planar curves is an improper indefinite affine spheres with singularities, and, reciprocally, every indefini…
The study classifies certain types of incomplete surfaces with low curvature.
problem Classifying incomplete affine spheres with specific curvature constraints.
method Analyzing total curvature and asymptotic behavior of surfaces.
result New examples of incomplete affine spheres with positive genus found.
We give a conformal representation for indefinite improper affine spheres which solve the Cauchy problem for their Hessian equation. As consequences, we can characterize their geodesics and obtain a generalized symmetry principle. Then, we classify the helicoidal indefinite improper affine spheres and find a new family…
There are exactly two different types of bi-dimensional improper affine spheres: the non-convex ones can be modeled by the center-chord transform of a pair of planar curves while the convex ones can be modeled by a holomorphic map. In this paper, we show that both constructions can be generalized to arbitrary even dime…
We give the best possible upper bound for the number of exceptional values of the Lagrangian Gauss map of complete improper affine fronts in the affine three-space. We also obtain the sharp estimate for weakly complete case. As an application of this result, we provide a new and simple proof of the parametric affine Be…
Bayesian evidence computation revisited for model selection with improper priors.
problem Model selection with improper priors and their impact on Bayesian evidence computation.
method Employing improper priors in model selection problems, distinguishing between Bayesian evidence and fake evidences.
result Diffuse priors asymptotically to infinity do not recover the area under the likelihood.
Improper affine spheres have played an important role in the development of geometric methods for the study of the Hessian one equation. Here, we review most of the advances we have made in this direction during the last twenty years.
FOLKLORE algorithm speeds up online multiclass logistic regression.
problem Efficiently solving online multiclass logistic regression without high computational cost.
method Developed FOLKLORE algorithm with improved runtime and regret bound.
result First practical algorithm for online multiclass logistic regression.
New algorithm reduces online logistic regression regret without exponential constant.
problem Improper learning in online logistic regression with logarithmic regret.
method Regularized empirical risk minimization with surrogate losses.
result Regret scaling as O(B log(Bn)) with low computational complexity.
The area distance to a convex plane curve is an important concept in computer vision. In this paper we describe a strong link between area distances and improper affine spheres. This link makes possible a better understanding of both theories. The concepts of the theory of affine spheres lead to a new definition of an …
This paper provides an algorithm for simulating improper (or noncircular) complex-valued stationary Gaussian processes. The technique utilizes recently developed methods for multivariate Gaussian processes from the circulant embedding literature. The method can be performed in operations, where…
We introduce a procedure for conditional density estimation under logarithmic loss, which we call SMP (Sample Minmax Predictor). This estimator minimizes a new general excess risk bound for statistical learning. On standard examples, this bound scales as with the model dimension and the sample size, and c…
We study the equation for improper (parabolic) affine spheres from the view point of contact geometry and provide the generic classification of singularities appearing in geometric solutions to the equation as well as their duals. We also show the results for surfaces of constant Gaussian curvatureand for developable s…
Given a Lagrangian submanifold of the affine symplectic -space, one can canonically and uniquely define a center-chord and a special improper affine sphere of dimension , both of whose sets of singularities contain . Although these improper affine spheres (IAS) always present other singularities away fro…
New algorithm reduces sample complexity for omnipredictors of SIMs.
problem Learning optimal predictors for various loss functions.
method Sharp analysis of Isotron algorithm for agnostic learning.
result Improved sample complexity to for bi-Lipschitz link functions.
We revisit the question of reducing online learning to approximate optimization of the offline problem. In this setting, we give two algorithms with near-optimal performance in the full information setting: they guarantee optimal regret and require only poly-logarithmically many calls to the approximation oracle per it…
New active learning framework for multiclass classification beyond realizability assumption.
problem Active learning in non-realizable settings with convex model classes.
method Surrogate risk minimization, epoch-based fitting, aggregation of models.
result Achieves label and sample complexity comparable to prior work in non-realizable settings.
Proposes a new SPVM model for RVM with more flexible priors.
problem Improper priors on multiple penalty parameters in RVM lead to improper posteriors.
method Introduces a single penalty approach (SPRVM) and a semi-Bayesian fitting method.
result SPRVM allows for more flexible priors and has proven conditions for posterior propriety.
Two machine learning models detect anomalies in ER claims, saving up to 40% in improper payments.
problem Improper health insurance payments from fraud and upcoding.
method Two machine learning models: an upcoding model based on severity code distributions and a random forest model for claim sorting.
result Random forest model saved 12% to 40% in improper payments compared to a baseline approach.
Bornological metrics on groups are studied, showing equivalence classes and constructing non-equivalent improper metrics.
problem Characterizing and constructing left-invariant metrics on groups that are not proper.
method Introducing bornological metrics and studying their equivalence classes, constructing non-equivalent improper metrics.
result Each coarse equivalence class of bornological metrics is determined by a bornology, and every class contains a canonical left-invariant representative.
Study shows memory needs grow with task sequence length in continual learning.
problem Challenges in retaining aptitude for multiple learning tasks sequentially.
method Complexity-theoretic study using communication complexity and multiplicative weights update.
result Memory needs grow linearly with task sequence length, suggesting intractability.
We study online prediction where regret of the algorithm is measured against a benchmark defined via evolving constraints. This framework captures online prediction on graphs, as well as other prediction problems with combinatorial structure. A key aspect here is that finding the optimal benchmark predictor (even in hi…
Study shows inefficiency of sparse linear regression learning with fewer than Ω(k^2) samples.
problem Efficiency of sparse linear regression learning with minimal samples.
method Reduction to sparse PCA problems and lower bounds.
result Efficient algorithms for sparse linear regression require at least Ω(k^2) samples.
New GP kernels avoid mean reversion without losing smoothness.
problem Pathological behavior in stationary GP regression.
method Improper Gaussian processes with non-positive kernels.
result Stationary, non-reverting covariance functions.
New insights into learning from only positive examples.
problem Characterizing proper learning from positive-only samples.
method Introducing a new combinatorial condition for proper positive-only learning.
result Proper positive-only learning is characterized by finite VC dimension and uniform exterior separability.
New bounds for non-convex estimators without Bernstein condition.
problem Sharp excess risk bounds for non-convex and improper estimators.
method Exponential-tail local Rademacher complexity risk bounds with offset condition.
result Sharp bounds for non-convex and improper estimators without Bernstein condition.
Author presents the second variational formula for statistical biharmonic maps.
problem Developing a formula for statistical biharmonic maps.
method Introduced the second variational formula for the statistical bi-energy functional.
result The second variational formula can be represented using Hessian curvature in Hessian manifolds.
Paper explores rate-preserving reductions between Blackwell approachability and no-regret learning.
problem Tackles rate-preserving reductions between Blackwell approachability and no-regret learning.
method Studies fine-grained reductions and optimal rates of convergence.
result Shows that rate-preserving reductions do not always hold, but provides conditions for when they do.
The paper studies a new class of affine maximal surfaces with singularities.
problem Understanding the properties of affine maximal surfaces with singularities.
method Defining a new subclass of affine maximal surfaces and applying Euclidean minimal surface theory.
result Affine maxfaces satisfy an Osserman-type inequality and do not contain non-trivial improper affine fronts.
The nonzero level sets in -dimensional flat affine space of a translationally homogeneous function are improper affine spheres if and only if the Hessian determinant of the function is equal to a nonzero constant multiple of the th power of the function. The exponentials of the characteristic polynomials of certa…
We study the problem of learning influence functions under incomplete observations of node activations. Incomplete observations are a major concern as most (online and real-world) social networks are not fully observable. We establish both proper and improper PAC learnability of influence functions under randomly missi…
Non-proper surface group action on product of trees found.
problem Proper surface group action on product of trees proposed, but not proper.
method Demonstrated non-properness of the surface group action.
result Surface group action on product of trees is not proper.
New DEC variant improves sample complexity bounds in decision making.
problem Understanding sample-efficient learning guarantees in decision making.
method Introducing a new Constrained Decision-Estimation Coefficient (DEC) and using it to derive improved lower bounds.
result New lower bounds improve upon prior work in three aspects: expectation, global applicability, and improper reference models.
We present a representation formula for discrete indefinite affine spheres via loop group factorizations. This formula is derived from the Birkhoff decomposition of loop groups associated with discrete indefinite affine spheres. In particular we show that a discrete indefinite improper affine sphere can be constructed …
We construct a complete, bounded Legendrian immersion in C^3. As direct applications of it, we show the first examples of a weakly complete bounded flat front in hyperbolic 3-space, a weakly complete bounded flat front in de Sitter 3-space, and a weakly complete bounded improper affine front in R^3.
New statistical biharmonic maps derived from a variation problem.
problem Variation problem for mappings between statistical manifolds.
method Statistical biharmonic maps derived from the Euler-Lagrange equation.
result Improper affine hyperspheres induce examples of statistical biharmonic maps.
Paper proposes a smart neck-band for detecting neck postures using integrated kinematic and kinetic data.
problem Improper neck postures lead to musculoskeletal disorders requiring therapy and rehabilitation.
method Integrated use of kinematic and kinetic data with machine learning algorithms.
result 100% accuracy in predicting neck postures using the proposed platform.
We present in this article a survey of recent results in value distribution theory for the Gauss maps of several classes of immersed surfaces in space forms, for example, minimal surfaces in Euclidean -space (=3 or 4), improper affine spheres in the affine 3-space and flat surfaces in hyperbolic 3-space. In parti…
Dropout, a stochastic regularisation technique for training of neural networks, has recently been reinterpreted as a specific type of approximate inference algorithm for Bayesian neural networks. The main contribution of the reinterpretation is in providing a theoretical framework useful for analysing and extending the…