Research
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.

168,742 papers · 148 categories

Trend · papers per month

6491,2981,9472,596 · Jun 202019922001200920172026
48 results for equivalence of oblivious tree structure

Nowadays, deep neural networks (DNNs) have become the main instrument for machine learning tasks within a wide range of domains, including vision, NLP, and speech. Meanwhile, in an important case of heterogenous tabular data, the advantage of DNNs over shallow counterparts remains questionable. In particular, there is …

2019-09-13abs ↗pdf ↗

Symmetric TSP is structurally equivalent to a constrained Group Steiner Tree Problem.

problem Finding the shortest tour in a symmetric TSP.
method Structural equivalence between symmetric TSP and constrained Group Steiner Tree Problem.
result Maximizing net weight in the cGSTP is equivalent to minimizing the TSP tour length.

The paper tackles pure exploration in multi-armed bandits with low rank structure using oblivious sampling.

problem Pure exploration in multi-armed bandits with low rank reward sequences.
method The approach involves separating the exploration strategy from feedback, using oblivious sampling, and incorporating kernel information of reward vectors.
result Efficient algorithms with regret bound O(d(lnN)/n)O(d\sqrt{(\ln N)/n}) for both time-varying and fixed cases, with a lower bound gap of O(lnN)O(\sqrt{\ln N}).

Leveraging an equivalence property in the state-space of a Markov Decision Process (MDP) has been investigated in several studies. This paper studies equivalence structure in the reinforcement learning (RL) setup, where transition distributions are no longer assumed to be known. We present a notion of similarity betwee…

2019-10-09abs ↗pdf ↗

Paper tackles robust estimation of tree-structured Ising models without side information.

problem Learning tree-structured Ising models with flipped signs of variables.
method Proves unidentifiability, proposes an algorithm with logarithmic sample complexity and polynomial run-time complexity.
result Empirically demonstrates robustness of proposed algorithm in the flipped signs setting.

Smooth fractal trees via analytic generators, preserving combinatorial and geometric properties.

problem Constructing smooth fractal trees from discrete models.
method Using analytic generator fields to integrate smooth vector fields in an internal state space, generating geometric curves as projections of generator trajectories.
result Analytic generators can represent any discrete tree specification and preserve the asymptotic limit geometry.

We study the bilipschitz equivalence type of tree-graded spaces, showing that asymptotic cones of relatively hyperbolic groups (resp. asymptotic cones of groups containing a cut-point) only depend on the bilipschitz equivalence types of the pieces in the standard (resp. minimal) tree-graded structure. In particular, th…

2012-04-03abs ↗pdf ↗

Study non-oblivious adversarial bandits with delayed feedback and propose algorithms with improved regret bounds.

problem Adversarial bandit problem with delayed, composite anonymous feedback.
method Propose wrapper algorithm for non-oblivious delay setting, achieving o(T)o(T) policy regret.
result Achieve o(T)o(T) policy regret for many adversarial bandit problems with bounded memory loss sequences.

Optimal subspace embedding with near-optimal sparsity for high-dimensional data.

problem Efficiently preserving norms of vectors in high-dimensional subspaces.
method Near-optimal sparsity oblivious subspace embedding with decoupling argument and cumulant method.
result Achieved near-optimal sparsity of O~(1/ε)\tilde O(1/ε) non-zeros per column.

In this paper we investigate the problem of estimating the cluster tree for a density ff supported on or near a smooth dd-dimensional manifold MM isometrically embedded in RD\mathbb{R}^D. We analyze a modified version of a kk-nearest neighbor based algorithm recently proposed by Chaudhuri and Dasgupta. The main res…

2013-07-24abs ↗pdf ↗

Paper proves equivalence of two Floer theories using pearly trees and Hamiltonian flows.

problem Proving equivalence between two Floer theories.
method Using pearly tree discs and local Hamiltonian flows.
result Equivalence relation between immersed Lagrangian Floer theory and Hamiltonian immersed Lagrangian Floer theory.

New algorithm recovers graph structure from noisy data.

problem Noise corrupts structure in Gaussian graphical models, making identification impossible.
method Developed an algorithm to recover graph structure up to an unavoidable ambiguity.
result Algorithm recovers graph structure up to an identified ambiguity, revealing local clustering and connectivity.

Study the tradeoffs of bandit feedback in multiclass classification.

problem The price of using bandit feedback in multiclass classification.
method Mistake bound model, analysis of variants, and comparison of learners and adversaries.
result The optimal mistake bound under bandit feedback is at most O(k)O(k) times higher than in full information, with a tight bound of O(k)O(k).

We provide new examples of acylindrically hyperbolic groups arising from actions on simplicial trees. In particular, we consider amalgamated products and HNN-extensions, 1-relator groups, automorphism groups of polynomial algebras, 3-manifold groups and graph products. Acylindrical hyperbolicity is then used to obtain …

2013-10-23abs ↗pdf ↗

Improved algorithm for partial recovery of tree-structured graphs with noisy data.

problem Learning Ising tree models with noisy observations.
method Symmetrized Geometric Averaging (SGA) algorithm with improved sample complexity.
result Significantly better sample complexity for partial tree recovery.

There is a well-known correspondence between infinite trees and ultrametric spaces which can be interpreted as an equivalence of categories and comes from considering the end space of the tree. In this equivalence, uniformly continuous maps between the end spaces are translated to some classes of coarse maps (or even c…

2007-04-24abs ↗pdf ↗

Consider jointly Gaussian random variables whose conditional independence structure is specified by a graphical model. If we observe realizations of the variables, we can compute the covariance matrix, and it is well known that the support of the inverse covariance matrix corresponds to the edges of the graphical model…

2019-01-25abs ↗pdf ↗

New study shows data-oblivious attacks can outperform data-aware ones.

problem Comparing effectiveness of data-oblivious and data-aware poisoning attacks.
method Theoretical study of feature selection with LASSO, focusing on separation between full-information and oblivious attackers.
result Data-oblivious attacks can achieve the same results as full-information attacks for feature selection with LASSO.

In [9] Kaimanovich introduced the concept of augmented tree on the symbolic space of a self-similar set. It is hyperbolic in the sense of Gromov, and it was shown in [13] that under the open set condition, a self-similar set can be identified with the hyperbolic boundary of the tree. In the paper, we investigate in det…

2012-05-16abs ↗pdf ↗

This paper clarifies vine copula structures using graph and matrix representations.

problem Ambiguity in vine copula representations in literature.
method Graph and matrix representations to clarify vine structures, including cherry and chordal sequences.
result A unique matrix representation of vine structures when given a perfect elimination ordering.

A directed acyclic graph (DAG) is the most common graphical model for representing causal relationships among a set of variables. When restricted to using only observational data, the structure of the ground truth DAG is identifiable only up to Markov equivalence, based on conditional independence relations among the v…

2018-02-05abs ↗pdf ↗

We show that the Gromov boundary of the free factor graph for the free group Fn with n>2 generators is the space of equivalence classes of minimal very small indecomposable projective Fn-trees without point stabilizer containing a free factor equipped with a quotient topology. Here two such trees are equivalent if the …

2012-11-07abs ↗pdf ↗

HS improves tree-based models' accuracy and interpretability without changing their structure.

problem Overfitting in tree-based models.
method Hierarchical Shrinkage (HS) post-hoc algorithm that shrinks tree predictions towards ancestor means.
result HS significantly improves predictive performance and interpretability of decision trees and RFs.

Space partitions of Rd\mathbb{R}^d underlie a vast and important class of fast nearest neighbor search (NNS) algorithms. Inspired by recent theoretical work on NNS for general metric spaces [Andoni, Naor, Nikolov, Razenshteyn, Waingarten STOC 2018, FOCS 2018], we develop a new framework for building space partitions re…

2019-01-24abs ↗pdf ↗

We provide high-probability sample complexity guarantees for exact structure recovery and accurate predictive learning using noise-corrupted samples from an acyclic (tree-shaped) graphical model. The hidden variables follow a tree-structured Ising model distribution, whereas the observable variables are generated by a …

2018-12-11abs ↗pdf ↗

New features generated from kernel methods are minimally dependent on sensitive features.

problem Generating fair features in the presence of sensitive and non-sensitive features.
method Relaxed Maximum Mean Discrepancy criterion, Hilbert-space-valued conditional expectation, plug-in approach.
result Closed-form solution for minimizing dependencies between new and sensitive features.

New algorithms for GLMs with oblivious noise, identifying solutions even when half the data is corrupted.

problem Regression for GLMs with additive oblivious noise.
method Distribution-independent algorithms that return accurate estimates or candidate solutions.
result First algorithmic result for GLM regression with oblivious noise, handling more than half corrupted data.

Improved upper bound for online calibrated forecasting of binary sequences.

problem Online calibrated forecasting of binary sequences.
method Introducing a variant of Qiao & Valiant's sign preservation game called sign preservation with reuse (SPR) and proving its equivalence to calibrated forecasting.
result Improved upper bound of O(T2/3ε)O(T^{2/3 - \varepsilon}) for calibrated forecasting, improving the O(T2/3)O(T^{2/3}) bound of Foster & Vohra.

New insights into variable selection with different model assumptions.

problem Sparse recovery with \ell_\infty error guarantees in variable selection.
method Separation between oblivious and adaptive models of \ell_\infty sparse recovery.
result Proves a surprising contrast between oblivious and adaptive models in \ell_\infty sparse recovery.

We present an extension of Monte Carlo Tree Search (MCTS) that strongly increases its efficiency for trees with asymmetry and/or loops. Asymmetric termination of search trees introduces a type of uncertainty for which the standard upper confidence bound (UCB) formula does not account. Our first algorithm (MCTS-T), whic…

2018-05-23abs ↗pdf ↗

New insights into pseudo-Anosov flows with special periodic orbits.

problem Understanding pseudo-Anosov flows with periodic orbits in 3-manifolds.
method Analyzing the topological features corresponding to trees of scalloped regions and classifying flows with the same free homotopy data.
result Explicit examples of flows with the same free homotopy data but not orbit equivalent.

A new data-oblivious sketch for logistic regression reduces data size while maintaining approximation accuracy.

problem Efficiently solving logistic regression in one pass over a data stream.
method Data-oblivious sketching approach that reduces data size to poly(μdlog n) weighted points.
result Sketching reduces data size significantly and provides approximation guarantees.

Probabilistic label trees improve XMLC by organizing labels hierarchically.

problem Efficiently tagging instances with a small subset of relevant labels from a large pool.
method Introduce and analyze probabilistic label trees (PLTs) as a generalization of hierarchical softmax for multi-label problems.
result PLTs are consistent for various performance metrics and can be trained online without prior knowledge.

Motivated by the work of Leininger on hyperbolic equivalence of homotopy classes of closed curves on surfaces, we investigate a similar phenomenon for free groups. Namely, we study the situation when two elements g,hg,h in a free group FF have the property that for every free isometric action of FF on an R\mathbb{R}-…

2004-09-16abs ↗pdf ↗