The study finds discrete subgroups with full limit sets in higher rank Lie groups.
problem Finding discrete subgroups with full limit sets in higher rank Lie groups.
method Analyzing real semi-simple Lie groups of higher rank and providing criteria for discrete subgroups of G=SL(3,R). result Existence of discrete subgroups with full limit sets in higher rank Lie groups.
Study shows non-symmetric convex sets have full boundary limits.
problem Understanding boundaries of non-symmetric convex sets.
method Proved using proximal limit set analysis.
result Proximal limit set equals full projective boundary for non-symmetric irreducible divisible convex sets.
Random subgroups in hyperbolic spaces have full limit sets and bounded critical exponents.
problem Understanding stationary random subgroups in hyperbolic spaces.
method Analyzing limit sets and critical exponents of random subgroups.
result Random subgroups have full limit sets and bounded critical exponents.
The study connects Hilbert entropy to non-differentiability points of limit sets in flag spaces.
problem Understanding non-differentiability points in limit sets of convex projective structures.
method Introduces hyperplane conicality for θ-Anosov representations and uses it to prove properties of boundary maps. result Hilbert entropy is linked to the Hausdorff dimension of non-differentiability points in flag spaces.
We present online boosting algorithms for multilabel ranking with top-k feedback, where the learner only receives information about the top k items from the ranking it provides. We propose a novel surrogate loss function and unbiased estimator, allowing weak learners to update themselves with limited information. Using…
The paper connects geodesic flows and limit sets on visibility manifolds.
problem Understanding dynamics and ergodic properties on non-compact visibility manifolds.
method Analyzing geodesic flows and Patterson-Sullivan measures on visibility manifolds without conjugate points.
result The positivity of the Patterson-Sullivan measure of the Myrberg limit set is equivalent to the conservativity of the geodesic flow.
We present online boosting algorithms for multiclass classification with bandit feedback, where the learner only receives feedback about the correctness of its prediction. We propose an unbiased estimate of the loss using a randomized prediction, allowing the model to update its weak learners with limited information. …
New method for scalable set encoding with unbiased gradient approximation.
problem Limited expressive power and large set training issues in set functions.
method Universally MBC (UMBC) class of set functions and efficient MBC training algorithm.
result Unbiased approximation of full set gradient with constant memory overhead.
Classifies Zariski closures of positive representations in Lie groups.
problem Classifying Zariski closures of positive representations in Lie groups.
method Classifies the Lie algebra of the Zariski closure of a discrete subgroup with specific properties.
result Obtains a new proof of Guichard's classification of Zariski closures of Hitchin representations.
Study on hyperconvex representations of surface groups and their geometric properties.
problem Understanding the geometry of hyperconvex representations of surface groups.
method Holomorphic extension of Ahlfors--Bers map and analysis of limit sets.
result Limit set has Hausdorff dimension 1 if and only if representation is in PSL(d,R).
Efficiently learns Ising model parameters with limited statistics.
problem Learning Ising model parameters with limited sample configurations.
method Examines trade-offs between computation and observation, using Ising model as example.
result Reconstructs model parameters with statistics up to order O(γ) for ℓ1 width γ. Paper generalizes Higgs bundle limits to parabolic setting.
problem Generalizing Higgs bundle limits to parabolic setting.
method Gauge theoretic construction of moduli space of parabolic Higgs bundles.
result Conformal limit always exists and defines holomorphic sections.
Study on Hausdorff dimension of Anosov subgroup limit sets under specific affine complexity.
problem Investigating the Hausdorff dimension of Anosov subgroup limit sets with self-affine complexity.
method Analyzing the Hausdorff dimension of projective limit sets Λ1(Γ) of Anosov subgroups Γ under specific assumptions about their affine complexity. result The Hausdorff dimension of Λ1(Γ) is determined by the critical exponent of the first simple root under partial quasi-self-similarity. Current neural network-based classifiers are susceptible to adversarial examples even in the black-box setting, where the attacker only has query access to the model. In practice, the threat model for real-world systems is often more restrictive than the typical black-box model where the adversary can observe the full …
Develops accelerated methods for optimization using low-dimensional projected-gradient information.
problem Optimization with low-dimensional projected-gradient information and Nesterov acceleration.
method Randomized-subspace Nesterov accelerated gradient methods for smooth convex and strongly convex optimization.
result Established accelerated oracle-complexity guarantees and unified basis for comparing sketch families.
New algorithm tackles multi-player bandit problems with limited access to arms.
problem Limited access to dynamic local subsets of arms in multi-player multi-armed bandit problems.
method Adopted Upper Confidence Bound (UCB) for exploration-exploitation and distributed optimization for collisions.
result Proposes a decentralized algorithm with near-optimal regret guarantee.
Constructs supermartingale couplings with full marginals constraints.
problem Optimal transport for supermartingale couplings with multiple marginals.
method Markovian iteration of one-period optimal supermartingale couplings.
result Explicit construction of supermartingale processes solving optimal transport problem.
Develops an efficient approximation for full conformal prediction regions.
problem Computing exact full conformal prediction regions is computationally infeasible.
method Generates an approximate confidence region that can be efficiently computed.
result Introduces a new notion of thickness to quantify approximation tightness.
New algorithm for online convex minimization over integer lattice.
problem Online decision-making with nonlinear combinatorial objectives.
method Introduces online Latural-convex minimization and proposes efficient algorithms. result Tight regret bound for full information setting algorithm.
We propose Progressive Structure-conditional Generative Adversarial Networks (PSGAN), a new framework that can generate full-body and high-resolution character images based on structural information. Recent progress in generative adversarial networks with progressive training has made it possible to generate high-resol…
Let S=Γ\H be a hyperbolic surface of finite topological type, such that the Fuchsian group Γ≤PSL2(R) is non-elementary, and consider any generating set S of Γ. When sampling by an n-step random walk in π1(S)≅Γ with each step given by an element…
In this thesis we discuss machine learning methods performing automated variable selection for learning sparse predictive models. There are multiple reasons for promoting sparsity in the predictive models. By relying on a limited set of input variables the models naturally counteract the overfitting problem ubiquitous …
We study the problem of optimal trading using general alpha predictors with linear costs and temporary impact. We do this within the framework of stochastic optimization with finite horizon using both limit and market orders. Consistently with other studies, we find that the presence of linear costs induces a no-tradin…
New methods provide stable ranking without assumptions on data distributions.
problem Stability issues in ranking problems with noisy data.
method Developed a stability framework and two ranking operators.
result Guaranteed stability without assumptions on data distributions.
In our previous article [Rad16], we investigated the asymptotic behaviour of orthogonal Bianchi class B perfect fluids close to the initial singularity and proved the Strong Cosmic Censorship conjecture in this setting. In several of the statements, the case of a stiff fluid had to be excluded. The present paper fills …
Let Y be a Gromov-Hausdorff limit of complete Riemannian n-manifolds with Ricci curvature bounded from below. A point in Y is called k-regular, if its tangent is unique and is isometric to an k-dimensional Euclidean space. By \cite{B5}, there is k>0 such that the set of all k-regular point Rk h…
Adam's bias shifts from full-batch to max-margin of different norms for separable data.
problem Understanding Adam's implicit bias in the incremental batch setting.
method Analyzing incremental Adam on linearly separable data, constructing datasets, and using a proxy algorithm.
result Incremental Adam can converge to different max-margin classifiers depending on the dataset and batching scheme.
Stability results for complex Monge-Ampère equations in various classes.
problem Stability of solutions to complex Monge-Ampère equations.
method Weak stability results followed by Ck,α stability proofs. result Proves stability of solutions in relative full mass classes and on quasi-projective varieties.
Expectation propagation (EP) is a deterministic approximation algorithm that is often used to perform approximate Bayesian parameter learning. EP approximates the full intractable posterior distribution through a set of local approximations that are iteratively refined for each datapoint. EP can offer analytic and comp…
New method estimates large matrices' spectra from small sub-matrices.
problem Estimating large matrices' spectra when full matrix-vector products are not available.
method Free decompression based on free probability theory.
result Estimates eigenspectrum of impalpable matrices from small sub-matrices.
The study extends classical results on harmonic functions to Riemannian manifolds with non-tangential boundary limits.
problem Extending classical results on harmonic functions to Riemannian manifolds with non-tangential boundary limits.
method Investigated the restricted mean-value property on Riemannian manifolds, focusing on non-tangential boundary behavior.
result Extended a classical result of Fenton to non-positively curved Harmonic manifolds of purely exponential volume growth.
Extends Thompson sampling for RL with fewer episodes.
problem Limited episodes in RL settings.
method Batch Bayesian optimization over episodes to learn action bias terms.
result Significantly outperforms standard Thompson sampling.
New tensors reveal full curvature structure from Riemann tensor.
problem Limited information from Ricci contraction of Riemann tensor.
method Contracting double dual of Riemann tensor to reveal full curvature.
result New tensors provide canonical parents of Einstein tensor.
The paper analyzes Laplace learning for Gaussian measure data in infinite dimensions, proving convergence.
problem Analyzing Laplace learning for infinite-dimensional Gaussian measure data.
method Minimizes Dirichlet energy on a graph constructed from the full dataset.
result Proves pointwise convergence of the graph Dirichlet energy for Gaussian measure data.
Accumulation of standardized data collections is opening up novel opportunities for holistic characterization of genome function. The limited scalability of current preprocessing techniques has, however, formed a bottleneck for full utilization of contemporary microarray collections. While short oligonucleotide arrays …
Due to the ease of modern data collection, applied statisticians often have access to a large set of covariates that they wish to relate to some observed outcome. Generalized linear models (GLMs) offer a particularly interpretable framework for such an analysis. In these high-dimensional problems, the number of covaria…
Full-sampling (e.g., Q-learning) and pure-expectation (e.g., Expected Sarsa) algorithms are efficient and frequently used techniques in reinforcement learning. Q(σ,λ) is the first approach unifies them with eligibility trace through the sampling degree σ. However, it is limited to the tabular case, for large-scale …
Improves full conformal prediction for stochastic non-conformity measures.
problem Inability of existing conditions to guarantee full conformal prediction validity under stochastic settings.
method Introduces a new sufficient condition: Conditional Independence & Permutation Invariance in Distribution.
result Corrects the insufficient condition and provides a new sufficient condition for full conformal prediction validity.
Semistatic trading strategies can be taken to limits in discrete time.
problem Limits of semistatic trading strategies in discrete time.
method Analysis in full generality for a two-period model, and under a probabilistic condition for multi-period, multi-stock models.
result Pointwise limits of semistatic trading strategies are again semistatic strategies.
New algorithm reduces regret in strategic prediction problem.
problem Designing an IC algorithm with sublinear regret for strategic experts.
method Developed a new algorithm WSU-UX and proved a worst-case regret bound.
result WSU-UX suffers a Ω(T2/3) lower bound on regret. We study the problem of online path learning with non-additive gains, which is a central problem appearing in several applications, including ensemble structured prediction. We present new online algorithms for path learning with non-additive count-based gains for the three settings of full information, semi-bandit and…
The study uses Hidden Markov Models to analyze student enrollment patterns and academic performance.
problem Limited understanding of how enrollment patterns affect academic performance.
method Applied Hidden Markov Models to categorize enrollment strategies and compare academic outcomes.
result Mixed enrollment strategies lead to better academic performance, especially during part-time semesters.
New method uses few instruments to estimate complex causal effects.
problem Estimating causal effects with limited instruments in high-dimensional settings.
method Sequentially selects and combines instruments to estimate the treatment effect.
result Can reliably recover the treatment effect's projection onto the instrumented subspace.
Determinantal point processes (DPPs) have garnered attention as an elegant probabilistic model of set diversity. They are useful for a number of subset selection tasks, including product recommendation. DPPs are parametrized by a positive semi-definite kernel matrix. In this work we present a new method for learning th…
Proposes efficient Gaussian process approximations for large datasets.
problem Scalability issues in Gaussian processes for large data sets.
method Combines Vecchia approximations and inducing points methods.
result Efficient and accurate approximations for various data types.
SPARC improves continual learning with minimal memory and computational overhead.
problem Efficient continual learning for deep neural networks.
method Combines task-specific working memories and task-agnostic semantic memory.
result Significantly reduces parameter usage (6% of full-model surrogates) while maintaining performance.
I study the limit of a large random economy, where a set of consumers invests in financial instruments engineered by banks, in order to optimize their future consumption. This exercise shows that, even in the ideal case of perfect competition, where full information is available to all market participants, the equilibr…
A new method for predicting with confidence for complex models.
problem Lack of reliable confidence in high-stake decision-making models.
method Developed a full-CP for sparse high-order interaction model using homotopy mining.
result SHIM achieves comparable accuracy to complex models and superior statistical power.