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.

169,181 papers · 148 categories

Trend · papers per month

233465698930 · Jun 202019922001200920182026
48 results for algorithmic proof

Polynomial-time algorithm estimates mean with bounded covariance using differential privacy.

problem Estimating mean of a d-variate distribution with differential privacy constraints.
method Sum of Squares (SoS) exponential mechanism for polynomial-time differentially private estimation.
result First polynomial-time algorithm with O(d)O(d) samples for mean estimation under pure differential privacy.

We provide a proof of backpropagation algorithm in matrix notation.

problem The lack of a full induction proof of backpropagation algorithm in matrix notation.
method We provide a full induction proof of the BP algorithm in matrix notation, situating it in the framework of matrix differential calculus.
result We prove the validity of the backpropagation algorithm in inductive form.

Paper analyzes CDRL algorithms for reinforcement learning.

problem Understanding theoretical properties of CDRL algorithms.
method Introduces a framework to analyze CDRL algorithms, establishes the importance of the projected distributional Bellman operator, draws connections to Cramér distance, and proves convergence.
result Proof of convergence for sample-based categorical distributional reinforcement learning algorithms.

This research simplifies verification of machine learning systems using reparameterization.

problem Reduce or eliminate serious bugs in machine learning systems.
method Use proof assistants to construct machine-checked proofs of correctness, leveraging reparameterization to handle probabilistic claims.
result Demonstrates broad applicability of reparameterization to verify different types of machine learning systems.

We provide the first differentially private algorithms for controlling the false discovery rate (FDR) in multiple hypothesis testing, with essentially no loss in power under certain conditions. Our general approach is to adapt a well-known variant of the Benjamini-Hochberg procedure (BHq), making each step differential…

2015-11-12abs ↗pdf ↗

No standard compact Clifford-Klein forms found for exceptional Lie groups.

problem Proving the non-existence of standard compact Clifford-Klein forms for exceptional Lie groups.
method Computer-aided approach, algorithmic methods for classifying semisimple subalgebras, and invariant calculations.
result Proves the non-existence of standard compact Clifford-Klein forms for homogeneous spaces of exceptional Lie groups.

New IRL algorithm for continuous state spaces with formal guarantees.

problem Finding a reward function for expert behavior in continuous state spaces.
method Modeling the system using orthonormal functions and providing correctness proofs.
result Proof of correctness and formal guarantees on sample and time complexity.

There are three main thrusts to this article: a new proof of Levi's Enlargement Lemma for pseudoline arrangements in the real projective plane; a new characterization of pseudolinear drawings of the complete graph; and proofs that pseudolinear and convex drawings of KnK_n have n2+n^2+{}O(nlogn)(n\log n) and O(n2)(n^2), respect…

2015-11-21abs ↗pdf ↗

New framework reduces sum-of-squares proof degree, speeding up clustering and robust moment estimation.

problem Sum-of-squares proof optimization and faster algorithms for clustering and robust moment estimation.
method Introducing new variables to reduce the degree of sum-of-squares proofs.
result Significantly faster algorithms for clustering and robust moment estimation with the same statistical guarantees.

Improved Sinkhorn algorithm for UOT with near-linear complexity.

problem Solving the entropic regularized Unbalanced Optimal Transport problem efficiently.
method Geometric convergence analysis of Sinkhorn updates and primal solution properties.
result Near-linear time complexity for finding ε\varepsilon-approximate UOT solutions.

We give a combinatorial proof of a theorem first proved by Souto which says the following. Let M_1 and M_2 be simple 3-manifolds with connected boundary of genus g>0. If M_1 and M_2 are glued via a complicated map, then every minimal Heegaard splitting of the resulting closed 3-manifold is an amalgamation. This proof a…

2007-01-14abs ↗pdf ↗

Paper introduces proof-of-learning to verify ML model training.

problem No mechanism to prove ML model training parameters were obtained through optimization.
method Inspired by proof-of-work and verified computations, introduces proof-of-learning mechanism.
result Proves model training parameters were obtained through optimization with minimal adversary work.

Proof of existence and uniqueness of weighted Voronoi-Delaunay on polyhedral surfaces.

problem Existence and uniqueness of weighted Voronoi-Delaunay on polyhedral surfaces.
method Construct an isotopic map instead of edge-flipping algorithm, generalizing Dyer et al's method.
result Strict proof of existence and uniqueness of weighted Voronoi-Delaunay on polyhedral surfaces.

We construct a Kirby diagram of the rational homology ball used in "generalized rational blow-down" developed by Jongil Park. The diagram consists of a dotted circle and a torus knot. The link is simpler, but the parameters are a little complicate. Euclidean Algorithm is used three times in the construction and the pro…

2007-08-17abs ↗pdf ↗

We propose the kl-UCB ++ algorithm for regret minimization in stochastic bandit models with exponential families of distributions. We prove that it is simultaneously asymptotically optimal (in the sense of Lai and Robbins' lower bound) and minimax optimal. This is the first algorithm proved to enjoy these two propertie…

2017-02-23abs ↗pdf ↗

Direct proof shows adaptive gradient descent converges near-linearly for convex functions.

problem Proving near-linear convergence of adaptive gradient descent for convex functions.
method Direct Lyapunov-based argument for convex functions with unique minimizer.
result Direct proof of near-linear convergence for convex functions.