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.

168,695 papers · 148 categories

Trend · papers per month

16324864 · May 202619922001200920172026
48 results for Decision-Estimation Coefficient

Improved model-free reinforcement learning with decision-estimation coefficient.

problem Interactive decision making, including structured bandits and reinforcement learning.
method Combining Estimation-to-Decisions with optimistic estimation to achieve better regret bounds.
result Regret bounds for model-free reinforcement learning with value function approximation.

New bounds show complexity of adversarial decision making.

problem Understanding sample efficiency in adversarial decision making.
method New upper and lower bounds on Decision-Estimation Coefficient.
result Decision-Estimation Coefficient is necessary and sufficient for low regret in adversarial decision making.

New bounds for γγ-regret using modified Decision-Estimation Coefficient.

problem Statistical characterization of γγ-regret for complex bandit problems.
method Statistical characterization via γγ-DEC, a modified Decision-Estimation Coefficient.
result Upper and lower bounds for γγ-regret nearly match, showing fundamental limits.

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.

New complexity measure for interactive learning reduces regret to near-optimal levels.

problem Challenges in sample-efficient, adaptive learning algorithms for interactive decision making.
method Introduces the Decision-Estimation Coefficient and the Estimation-to-Decisions (E2D) principle.
result Unified algorithm design principle E2D achieves optimal sample-efficient learning.

Unified algorithm tackles various RL goals like reward-free and preference-based learning.

problem Unified approach to multiple RL learning goals.
method Decision-Estimation Coefficient (DEC) framework.
result Unified algorithm handles various learning goals with a single framework.

OE2D framework reduces contextual bandits to offline regression for near-optimal regret.

problem Efficiently learning contextual bandits with large action spaces and complex reward functions.
method Offline Estimation to Decisions (OE2D) algorithm that reduces contextual bandits to offline regression.
result Near-optimal regret for contextual bandits with large action spaces and O(logT)O(\log T) calls to an offline regression oracle.

Unified framework for lower bounds in interactive decision making.

problem Challenges in interactive decision making, especially bandits and reinforcement learning.
method Interactive Fano method and Fractional Covering Number.
result Unified characterization of learnability for stochastic bandit problems and tight lower bounds for interactive decision making.

Study shows offline RL under QQ^\star-approximation and partial coverage is harder than previously thought.

problem Theoretical limits of offline reinforcement learning under QQ^\star-approximation and partial coverage.
method Introduced a decision-estimation framework to decompose offline RL complexity into decision and value estimation errors.
result Answered the open question by proving sample inefficiency under partial coverage is not guaranteed by QQ^\star-realizability and Bellman completeness.

We characterize learnability for stochastic noisy bandits, identifying optimal query complexities.

problem Learnability of stochastic noisy bandit models.
method Complete characterization through model class analysis and proof of optimal query complexities.
result Characterization of learnability for stochastic noisy bandit models.

New algorithms reduce sample complexity for multiclass contextual bandits.

problem Designing efficient algorithms for multiclass contextual bandits with sparse rewards.
method Two complementary approaches: decision-estimation coefficient analysis and low-variance exploration.
result Achieved optimal sample complexity bounds for multiclass contextual bandits.

Framework reduces contextual bandit learning to offline regression with near-optimal regret.

problem Efficient learning with large action spaces and complex reward functions.
method Offline Estimation to Decisions (OE2D) algorithm that minimizes regret with near-optimal oracle calls.
result Near-optimal regret for contextual bandits with large action spaces and O(log(T))O(log(T)) offline oracle calls.

Framework for robust decision making in changing environments with privacy constraints.

problem Interactive decision making in changing environments with constraints.
method Hybrid Decision Making with Structured Observations (hybrid DMSO) framework, local differentially private decision making, query-based learning, robust and smooth decision making.
result Strong connections and bounds derived for DEC, SQ dimension, local minimax complexity, learnability, and joint differential privacy.

Study on multi-agent decision making complexity, showing sample efficiency gaps.

problem Understanding sample efficiency in multi-agent decision making.
method General framework for interactive decision making, focusing on equilibrium computation.
result No 'reasonable' complexity measure can close gaps between single and multiple agents.

We study optimal solutions to an abstract optimization problem for measures, which is a generalization of classical variational problems in information theory and statistical physics. In the classical problems, information and relative entropy are defined using the Kullback-Leibler divergence, and for this reason optim…

2010-12-02abs ↗pdf ↗

Machine learning predicts Kronecker coefficients with high accuracy.

problem Predicting Kronecker coefficients from tensor products of symmetric group representations.
method Training machine learning models (NN, CNN, GBDT) to classify Kronecker coefficients as zero or non-zero.
result Trained models achieve high accuracy (0.98\approx 0.98) in classifying Kronecker coefficients.

Abstract: Determines thermoelastic coefficients from boundary data.

problem Determining coefficients of thermoelastic system from boundary information.
method Explicit expression for thermoelastic Dirichlet-to-Neumann map with variable coefficients.
result Thermoelastic Dirichlet-to-Neumann map uniquely determines coefficients on the manifold.

New filling functions for groups with coefficients show different asymptotic behavior.

problem Difficulty in filling loops with surfaces in Cayley graphs.
method Defining homological filling functions with coefficients and proving their differences.
result Filling functions for nn-cycles with coefficients in different groups have distinct asymptotic behavior.

Abstract: Determines Lamé coefficients from boundary measurements.

problem Determining Lamé coefficients from elastic boundary measurements.
method Explicit symbol of elastic Dirichlet-to-Neumann map, partial derivatives determination.
result Elastic Dirichlet-to-Neumann map uniquely determines Lamé coefficients.

Defines and proves properties of weighted renormalized volume coefficients.

problem None explicitly stated; focuses on mathematical definitions and proofs.
method Defines weighted renormalized volume coefficients and proves their variational nature and polynomial representation.
result Weighted renormalized volume coefficients are variational and can be expressed as polynomials of specific tensors.

Improved 3D LiDAR data classification using product coefficients.

problem Enhancing accuracy in 3D LiDAR data classification.
method Introducing product coefficients derived from measure theory as additional features in the classification process, alongside PCA.
result Significant improvement in classification accuracy with product coefficients.

We study the structure of the stable coefficients of the Jones polynomial of an alternating link. We start by identifying the first four stable coefficients with polynomial invariants of a (reduced) Tait graph of the link projection. This leads us to introduce a free polynomial algebra of invariants of graphs whose ele…

2013-09-23abs ↗pdf ↗

Paper calculates third coefficient in Kaehler-Einstein metric expansion.

problem Understanding Kaehler-Einstein metrics and their epsilon functions.
method Computes the third coefficient in the TYCZ-expansion of the epsilon function.
result Discovers the vanishing of the third coefficient's significance.

Develops local elliptic regularity for geometrically-natural operators with low regularity coefficients.

problem Local elliptic regularity for operators with low regularity coefficients in Sobolev-type spaces.
method Rescaling estimates and multiplication results for function spaces.
result Unified set of interior estimates and regularity inference for operators with Sobolev-type coefficients.

Extends A-type coefficient polynomials to B-type setting, introducing new invariants.

problem Tackles the B-type skein relation and introduces new coefficient polynomials.
method Introduces coefficient polynomials associated with the B-type skein relation and proves their invariance under Reidemeister moves.
result Shows that the generating series of these coefficient polynomials recovers the Kauffman polynomial.

We simplify complex regression coefficients using linearization and feature comparison.

problem Interpreting high-dimensional regression coefficients from nonlinear responses.
method Developed a linearization method to derive feature coefficients and compare them with regression coefficients.
result Shows how regression coefficients relate to linearized feature coefficients and how they change under regularization.

Bounding twist number of surface links using polynomial coefficients.

problem Bounding the twist number of alternating surface links.
method Introducing a generalized homological Kauffman bracket and applying it to surface link diagrams.
result A bound for the twist number of alternating surface links in terms of polynomial coefficients.

Characterizes differential forms and vector fields with constant coefficients on manifolds.

problem Understanding constant coefficient differential forms and vector fields on manifolds.
method Analyzes differential forms and vector fields of specific degrees, proving obstructions and characterizing solutions to partial differential systems.
result Characterizes differential forms and vector fields with constant coefficients of various degrees on smooth manifolds.

Study on gradient descent in Hilbert spaces with Markov chains, focusing on mixing coefficients.

problem Analyzing convergence of gradient descent in Hilbert spaces with stationary Markov chains.
method Examined strictly stationary Markov chains with φφ- and ββ-mixing coefficients, derived probabilistic upper bounds.
result Probabilistic upper bounds on convergence behavior of gradient descent algorithm based on mixing coefficients.

The conformal powers of the Laplacian of a Riemannian metric which are known as the GJMS-operators admit a combinatorial description in terms of the Taylor coefficients of a natural second-order one-parameter family (˝r;g)\H(r;g) of self-adjoint elliptic differential operators. (˝r;g)\H(r;g) is a non-Laplace-type perturbation …

2014-11-28abs ↗pdf ↗

Guts determine the leading coefficients of L2L^2-Alexander torsions for 3-manifolds.

problem Determining the leading coefficient of L2L^2-Alexander torsions for 3-manifolds.
method Using a new criterion for the convergence of Fuglede-Kadison determinants and the work of Agol and Zhang on guts of 3-manifolds.
result The leading coefficient equals the relative L2L^2-torsion of the guts associated to the cohomology class.

Diffusion models adapt to low-dimensional data regardless of coefficient choices.

problem Understanding how diffusion models adapt to low-dimensional data structures.
method Analysis of diffusion models with flexible coefficient choices.
result Proven that O~(k/ε)\widetilde{O}(k/\varepsilon) iterations suffice for accurate sampling in total variation distance.

GenMod uses generative models to approximate high-dimensional PDE solutions with limited evaluations.

problem Quantifying uncertainty in high-dimensional PDE systems with random parameters.
method Develops a method using generative models to approximate polynomial chaos coefficients in underdetermined systems.
result The method outperforms sparsity-promoting methods in approximating PDE solutions with limited evaluations.

We prove the 33-manifold $\RP^3 \# \RP^3$ is of Z2\Z_{2}-coefficient homology (1,2)(1, 2)-systolic freedom. Given a Riemannian metric on $\RP^{3}\# \RP^{3}$, we define Z2\Z_{2}-coefficient homology 11-systole as the infimum of lengths of all nonseparating geodesic loops representing nontrivial classes in $H_{1}(\RP^3\#\…

2014-02-18abs ↗pdf ↗

The nullspace and regularization impact high-dimensional linear regression interpretability.

problem Interpreting high-dimensional linear regression coefficients in complex data.
method Optimization formulation to compare coefficients and physical knowledge.
result Regularization and z-scoring choices affect interpretability and true coefficient closeness.

Framework uses deep learning and statistical models to solve PDEs with discontinuous coefficients.

problem Solving PDEs with discontinuous coefficients.
method Two-stage physics-informed deep learning and statistical mixture models.
result Framework achieves adaptability and accurate parameter identification.

A fundamental property of complex networks is the tendency for edges to cluster. The extent of the clustering is typically quantified by the clustering coefficient, which is the probability that a length-2 path is closed, i.e., induces a triangle in the network. However, higher-order cliques beyond triangles are crucia…

2017-04-12abs ↗pdf ↗

The paper solves MMV and MV problems with random coefficients and finds shared optimal strategies.

problem Optimal trading strategies with random market coefficients.
method Backward stochastic differential equations (BSDEs) to find optimal strategies.
result MMV and MV problems share the same optimal portfolio and value under random coefficients.

We construct explicitly the Khovanov homology theory for virtual links with arbitrary coefficients by using the twisted coefficients method. This method also works for constructing Khovanov homology for ``non-oriented virtual knots'' in the sense of Viro, in particular, for knots in RP3{\bf R}P^{3}.

2006-01-08abs ↗pdf ↗