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.

169,291 papers · 148 categories

Trend · papers per month

67133200266 · Jun 202019922001200920182026
48 results for graph rewriting

System uses neural networks to prove program equivalence via rewrite rules.

problem Proving equivalence between two dataflow graphs.
method Developed a graph-to-sequence neural network trained on example generation to find semantics-preserving rewrite rules.
result System correctly outputs a rewrite sequence for 96% of program pairs, proving equivalence.

Zipper logic is a graph rewrite system, consisting in only local rewrites on a class of zipper graphs. Connections with the chemlambda artificial chemistry and with knot diagrammatics based computation are explored in the article.

2014-05-20abs ↗pdf ↗

Serenity optimizes neural network execution for edge devices by scheduling with optimal memory footprint.

problem Order of nodes in irregular neural networks affects memory footprint, complicating execution under resource constraints.
method Memory-aware compiler using dynamic programming and graph rewriting to find optimal schedules.
result Achieves optimal peak memory and further improves it with graph rewriting, reducing memory usage by 1.68x-1.86x compared to TensorFlow Lite.

Graph neural networks can perform approximate reasoning in latent space for mathematical statements.

problem Can neural networks perform steps of approximate reasoning in a fixed dimensional latent space?
method Design and conduct an experiment using graph neural networks to predict rewrite-success of mathematical statements in a latent space.
result Graph neural networks can make non-trivial predictions about rewrite-success of statements in latent space.

Autostackability for finitely generated groups is defined via a topological property of the associated Cayley graph which can be encoded in a finite state automaton. Autostackable groups have solvable word problem and an effective inductive procedure for constructing van Kampen diagrams with respect to a canonical fini…

2013-07-18abs ↗pdf ↗

NeuRewriter learns to choose and rewrite heuristics in combinatorial problems.

problem Time-consuming tuning of heuristics in combinatorial optimization.
method NeuRewriter uses reinforcement learning to learn a policy for picking heuristics and rewriting solutions.
result NeuRewriter outperforms existing methods in various combinatorial tasks.

This is the author's Master's thesis written under the supervision of Dr. Gregor Weingart at the National Autonomous University of Mexico. The purpose of this study is to rewrite differential supergeometry in terms of classical differential geometry. This rewriting from "first principles" has two main motivations: 1 av…

2014-10-29abs ↗pdf ↗

A fast metric learning framework using Gershgorin disc alignment.

problem Learning effective metrics for graph-based data.
method Fast projection-free metric learning via Gershgorin disc alignment.
result Efficiently computed graph metric matrices outperform competing methods.

NIFTy.re accelerates imaging models and expands Gaussian processes and variational inference.

problem Slow performance and limited inference strategies in NIFTy.
method Rewritten NIFTy with new modeling principles, inference strategies, and JAX integration.
result Dramatic acceleration of models and new inference capabilities.

Rewriting history improves RL algorithms for solving multiple tasks.

problem Improving sample efficiency in multi-task reinforcement learning.
method Introducing hindsight relabeling as inverse RL to generalize goal-relabeling techniques.
result Relabeling data using inverse RL accelerates learning in multi-task settings.

We give definition of a holonomy flag in subRiemannian geometry --- a generalization of a Riemannian holonomy algebra --- and calculate it for the 3D subRiemannian Lie groups. We rewrite and give new interpretation for the Codazzi equations for the (2,3)(2,3)-distributions on the SU(2)SU(2) and the Heisenberg group.

2015-12-07abs ↗pdf ↗

In this paper, a type of integrable evolution equation--the generalized Landau-Lifshitz equation into SnS^n is considered. We deal with this equation from a geometric point of view by rewriting it in a geometric form. Through the geometric energy method, we show the global well-posedness of the corresponding Cauchy pro…

2010-09-13abs ↗pdf ↗

Unified approach for multicalibration in weakly supervised learning.

problem Existing multicalibration methods require clean input-label pairs, which are unavailable in weakly supervised learning.
method Developed estimators and post-hoc correction methods for multicalibration under weak supervision.
result Unified framework for estimating and correcting multicalibration under weak supervision with finite-sample guarantees.

We consider normal almost contact structures on a Riemannian manifold and, through their associated sections of an ad-hoc twistor bundle, study their harmonicity, as sections or as maps. We rewrite these harmonicity equations in terms of the Riemann curvature tensor and find conditions relating the harmonicity of the a…

2011-09-09abs ↗pdf ↗

PaRoT simplifies robust training for deep neural networks.

problem Training deep neural networks to be robust to small input changes.
method Developed a practical framework on TensorFlow for robust training without code modifications.
result PaRoT's performance is comparable to existing methods and is easy to use on real-world models.

We revisit the cohomological index theorem for elliptic elements in the universal enveloping algebra of a Lie groupoid previously proved by the authors. We prove a Thom isomorphism for Lie algebroids which enables us to rewrite the "topological side" of the index theorem. This results in index formulae for Lie groupoid…

2013-08-01abs ↗pdf ↗

In this note we study conformal Ricci flow introduced by Arthur Fischer. We use DeTurck's trick to rewrite conformal Ricci flow as a strong parabolic-elliptic partial differential equations. Then we prove short time existences for conformal Ricci flow on compact manifolds as well as on asymptotically flat manifolds. We…

2011-09-25abs ↗pdf ↗

Existence proved for complex 3-folds equation on a specific phase range.

problem Existence of solutions for a specific equation on complex 3-folds.
method New continuity path and Monge-Ampère equation with mixed sign coefficients.
result Existence result for the deformed Hermitian Yang-Mills equation on compact complex three-folds.

Mikhail Khovanov in math.QA/9908171 defined, for a diagram of an oriented classical link, a collection of groups numerated by pairs of integers. These groups were constructed as homology groups of certain chain complexes. The Euler characteristics of these complexes are coefficients of the Jones polynomial of the link.…

2002-02-20abs ↗pdf ↗

Investigates surfaces with prescribed mean and skew curvatures in Lorentz-Minkowski space.

problem Finding surfaces with prescribed mean and skew curvatures in Lorentz-Minkowski space.
method Rewriting the equations for mean and skew curvatures as linear first order ODEs with coefficients in hypercomplex numbers or real numbers.
result Solutions for surfaces of revolution with prescribed mean and skew curvatures.

Viewing Dehn's algorithm as a rewriting system, we generalise to allow an alphabet containing letters which do not necessarily represent group elements. This extends the class of groups for which the algorithm solves the word problem to include nilpotent groups, many relatively hyperbolic groups including geometrically…

2007-06-20abs ↗pdf ↗

A new framework for personalized ad retrieval in e-commerce search.

problem Difficulty in measuring ads retrieved using multiple signals (e.g. user profiles, clicks).
method Employing historical click data to initialize a hierarchical network representing signals, keys, and ads. Training a model to learn weights of edges and selecting the best edges.
result Framework achieves good performance, improving RPM/CTR.

We reformulate ten-dimensional type II supergravity as a generalised geometrical analogue of Einstein gravity, defined by an O(9,1)×O(1,9)O(10,10)×R+O(9,1)\times O(1,9)\subset O(10,10)\times\mathbb{R}^+ structure on the generalised tangent space. Using the notion of generalised connection and torsion, we introduce the analogue of the Levi-C…

2011-07-08abs ↗pdf ↗

We consider the Dirac equation in flat Minkowski 3-space and rewrite it as the Maxwell equation in Minkowski 4-space with torsion. The torsion tensor is defined as the dual of the electromagnetic vector potential. Our model clearly distinguishes the electron and the positron without resorting to "negative frequencies":…

2000-06-17abs ↗pdf ↗

Study harmonicity of normal almost contact structures on Riemannian manifolds.

problem Understanding harmonicity of normal almost contact structures.
method Analyzing harmonicity through associated sections of a twistor bundle and rewriting equations in terms of curvature tensor.
result Conditions relating harmonicity of almost contact metric and almost complex structures.

The paper solves optimal control problems for stochastic delay equations.

problem Optimal control of stochastic delay differential equations.
method Rewriting the problem in an infinite-dimensional Hilbert space, using dynamic programming and viscosity solutions.
result Characterizes the value function as the unique viscosity solution of the Hamilton-Jacobi-Bellman equation.

Many machine learning algorithms minimize a regularized risk, and stochastic optimization is widely used for this task. When working with massive data, it is desirable to perform stochastic optimization in parallel. Unfortunately, many existing stochastic optimization algorithms cannot be parallelized efficiently. In t…

2014-06-17abs ↗pdf ↗

AI agents manage portfolios, improving on human oversight.

problem Improving strategic asset allocation for institutional investors.
method 50 specialized agents produce capital market assumptions, construct portfolios, critique, and vote on each other's output.
result Meta-agent compares forecasts with realized returns and improves agent performance.

While the fundamental object in Riemannian geometry is a metric, closed string theories call for us to put a two-form gauge field and a scalar dilaton on an equal footing with the metric. Here we propose a novel differential geometry which treats the three objects in a unified manner, manifests not only diffeomorphism …

2011-05-31abs ↗pdf ↗

New insights into using momentum for non-convex optimization.

problem Improving training of non-convex models like deep neural networks.
method Developed a Lyapunov analysis of SGD with momentum using stochastic primal averaging.
result Precise conditions under which SGD+M outperforms SGD and optimal hyper-parameter schedules.