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

326495127 · May 202619922001200920172026
48 results for partially lifted RDT

Wide hidden layer TCM nets capacity analyzed using RDT and fl RDT.

problem Capacity analysis of wide hidden layer TCM nets.
method Employed Fully Lifted Random Duality Theory (fl RDT) for capacity characterization.
result Explicit, closed form capacity characterizations for a generic class of hidden layer activations.

New method lowers spherical perceptron capacity using fully lifted random duality theory.

problem Tackles the negative spherical perceptron capacity, a long-standing open problem.
method Develops fully lifted random duality theory (fl RDT) to characterize capacity.
result Shows remarkable closed-form analytical relations for practical capacity values.

Improved neural network capacity analysis using simplified RDT.

problem Analyzing the memorization capabilities of sign perceptron neural networks.
method Developed a simplified, partially lifted Random Duality Theory (fl RDT) approach.
result Concrete capacity bounds universally improve over previous best known ones.

New analysis shows capacity of treelike neural networks with various activations.

problem Analyzing the capacity of treelike neural networks with diverse activations.
method Utilized Random Duality Theory and its partially lifted version to handle various activations.
result The capacity of treelike neural networks decreases for large network width but converges to a constant value.

Study potential computational gaps in symmetric binary perceptrons using fl-RDT.

problem Potential statistical-computational gaps in symmetric binary perceptrons.
method Parametric utilization of fully lifted random duality theory (fl-RDT).
result Observation of a computational gap SCG=αcαaSCG=α_c-α_a in SBP.

This paper connects ultrametric overlap gap properties to parametric RDT for symmetric binary perceptrons.

problem Characterizing statistical computational gaps in symmetric binary perceptrons.
method Developed an analytical union-bounding program to rigorously upper-bound constraint densities of ultrametric overlap gap properties.
result Obtained tightest bounds at the first two levels of ultrametric overlap gap properties, closely approaching parametric RDT estimates.

The study calculates the injectivity capacity of ReLU networks using a novel mathematical approach.

problem Determining the injectivity capacity of ReLU networks layers.
method Employing fully lifted random duality theory (fl RDT) to handle the 0\ell_0 spherical perceptron and implicitly the ReLU layers injectivity.
result The lifting mechanism converges remarkably fast with relative corrections not exceeding 0.1%.

Study on theoretical limits of 0\ell_0 sparse-regression algorithms using Fl RDT.

problem Understanding the performance limits of 0\ell_0 norm based optimization algorithms in compressed sensing and sparse regression.
method Utilized Fully lifted random duality theory (Fl RDT) to analyze the maximum-likelihood (ML) decoding performance.
result Uncovered phase-transition (PT) and descending 0\ell_0 (d0\ell_0) curves that separate successful and unsuccessful algorithm performance.

Study binary perceptrons' capacity using random duality theory.

problem Characterize the capacity of binary perceptrons with general thresholds.
method Utilized fully lifted random duality theory (fl RDT) to characterize the capacity.
result Characterizations match replica symmetry breaking predictions and uncover the capacity for zero-threshold scenario.

New insights into binary perceptron reveal phase transitions and algorithmic thresholds.

problem Understanding the statistical-computational gap in binary perceptron models.
method Application of fully lifted random duality theory (fl RDT) to uncover structural changes.
result Numerical estimates of constraint density thresholds align with theoretical predictions.

This work adapts RDT for mental program construction, showing benefits and costs.

problem Applying RDT to mental programs with trade-offs between description length, error, and computational costs.
method Proposed a three-way trade-off and used simulations and partial information decomposition.
result Constructing a shared program library provides global benefits but is sensitive to curricula.

New method finds rare dense clusters in asymmetric binary perceptrons, resolving algorithmic hardness.

problem Resolving algorithmic hardness in asymmetric binary perceptrons.
method Fully lifted random duality theory (fl RDT) and large deviation upgrade (sfl LD RDT).
result Local entropy breaks down for constraint densities in (0.77, 0.78) interval, matching current solver limits.

CLuP achieves near optimal ground state energies for positive and negative Hopfield models.

problem Finding near optimal ground state energies for positive and negative Hopfield models.
method Controlled Loosening-up (CLuP) algorithm with fully lifted random duality theory (fl RDT).
result Achieves ground state free energies of 1.771.77 and 0.330.33 for positive and negative Hopfield models respectively.

The study revisits Hopfield's associative memory model and calculates its capacity for two specific pattern basins.

problem Determining the capacity of a Hebbian-Hopfield network for storing binary patterns.
method Using fully lifted random duality theory and numerical analysis, the study calculates the capacity for two specific pattern basins.
result Explicit characterizations of the capacity for the AGS and NLT pattern basins, with remarkable fast lifting convergence.

New algorithms handle phase retrieval with rank d measurements, revealing phase transitions.

problem Phase retrieval with rank d measurements.
method Random duality theory (RDT) and descending phase retrieval algorithms (dPR).
result Minimal sample complexity ratio for dPR's success exhibits phase transitions.

Study precise sample covariance error for Gaussian centered data.

problem Precise characterization of sample covariance error for Gaussian data.
method Developed a Random Duality Theory (RDT) framework to determine upper and lower bounds.
result Upper and lower bounds match in large-dimensional contexts, matching the spectral norm's limiting value.

Descending phase retrieval algorithms show a phase transition with increasing sample complexity.

problem Theoretical limits of descending phase retrieval algorithms.
method Utilizing Random duality theory (RDT), the study develops a generic program to characterize algorithm performance.
result As sample complexity increases, the parametric manifold transitions from multi to single funneling points, leading to a phase transition in algorithm success.

Study connects symmetries in dynamical systems to phase plane representations.

problem Understanding symmetries in dynamical systems and their phase plane realizations.
method Analysis of symmetries in differential equations and phase plane representations, establishing correspondence and lifting conditions.
result Every symmetry generator in one formulation corresponds uniquely to a generator in the other, with a lifting condition to solve.

New bounds on neural network capacity for treelike sign perceptrons using RDT.

problem Determining the capacity of treelike sign perceptrons neural networks.
method Random Duality Theory (RDT) to establish upper bounds.
result Mathematically rigorous bounds on network capacity for any number of neurons.

We connect Causal inference and low-rank recovery via RDT and free probability theory.

problem Determining the applicability of causal inference via low-rank recovery.
method Random Duality Theory, free probability theory, and mathematical rigor.
result Exact closed-form worst case phase transitions for causal inference.

Develops a lifting theory for exponential maps in semi-Riemannian geometry.

problem Overcoming singularities in exponential maps to prove geodesic connectivity.
method Lifting theory for semi-Riemannian manifolds with path-continuation property.
result General path-lifting theorem extending globally under certain conditions.

We analyze ridge interpolators in correlated factor regression models using RDT.

problem Performance analysis of ridge interpolators in correlated factor regression models.
method Utilizing Random Duality Theory (RDT), we obtain precise closed form characterizations of optimization problems.
result Ridge interpolators can smooth out the excess prediction risk and exhibit double-descent behavior.

Study shows certain diffeomorphisms cannot be dynamically coherent.

problem Dynamically coherent behavior in partially hyperbolic diffeomorphisms.
method Analyzes pseudo-Anosov components and Nielsen-Thurston classification.
result Extends previous work to larger class of diffeomorphisms.

Study detects non-trivial elements in diffeomorphism groups via trivalent graphs.

problem Detecting non-trivial elements in homotopy groups of diffeomorphism spaces.
method Using Kontsevich classes and trivalent graphs, we lift elements from one moduli space to another.
result Non-trivial elements in π(BDiff(Dd))Qπ_*(B\mathrm{Diff}_{\partial}(D^d))\otimes \mathbb{Q} are lifted to π(BDiff(DdimesI))Qπ_*(B\mathrm{Diff}_{\sqcup}(D^d imes I))\otimes \mathbb{Q} and π(Mpsc(Dd)h0)Qπ_*(\mathcal{M}^{\mathrm{psc}}_{\partial}(D^d)_{h_0})\otimes \mathbb{Q}.

We consider stochastic partial differential equations appearing as Markovian lifts of matrix valued (affine) Volterra type processes from the point of view of the generalized Feller property (see e.g., \cite{doetei:10}). We introduce in particular Volterra Wishart processes with fractional kernels and values in the con…

2019-07-02abs ↗pdf ↗

New algorithm nearly achieves ground state free energy of SK model.

problem Determining the ground state free energy of the SK model.
method Controlled Loosening-up (CLuP) algorithm applied to SK models.
result Achieves ground state free energy of ~0.76 for n in the thousands.

The paper solves the Nielsen realization problem for high degree del Pezzo surfaces.

problem Which finite subgroups of the mapping class group of a del Pezzo surface lift to the diffeomorphism group?
method Classification and partial answers for d7d \geq 7, equivariant connected sum for d=6d = 6.
result Complete classification for d7d \geq 7, partial answer for d=6d = 6.

A new spectrum recovers cobordism cut and paste groups of manifolds with boundary.

problem Defining and studying cobordism cut and paste groups of manifolds with boundary.
method Constructing a spectrum that recovers the cobordism cut and paste groups of manifolds with boundary.
result Construction of a spectrum that recovers the cobordism cut and paste groups of manifolds with boundary.

Model rough volatility using RDEs with correlated Brownian motion and fractional Brownian motion.

problem Modeling rough volatility with correlated stochastic processes.
method Developed a method to lift Brownian motion and rough paths, applying it to fractional Brownian motion to model rough volatility.
result Calibrated a new rough volatility model to market data.

Deep ReLU networks show that 4 layers suffice for unique input recovery.

problem Injectivity capacity of deep ReLU networks.
method Developed a program connecting deep ReLU injectivity to an ll-extension of the 0\ell_0 spherical perceptrons, using random duality theory.
result Only 4 layers are needed for unique input recovery, showing expansion saturation effect.

Cut-DeepONet handles discontinuities and sharp transitions in neural operators.

problem Neural operators struggle with discontinuities and sharp transitions in PDEs.
method Two-stage training framework that explicitly models discontinuities via a lifting strategy and input-dependent discontinuity prediction.
result Cut-DeepONet outperforms state-of-the-art methods on benchmark PDEs with low-resolution datasets.

Horizontal endomorphisms, almost complex structures, vertical, horizontal and complete lifts on prolongation of a Lie algebroid are considered. Then using exact sequences, semisprays are constructed. Moreover, important geometrical objects such as classical distinguished connections, torsions and partial curvatures are…

2013-10-28abs ↗pdf ↗

Study lift metrics and connections on tangent bundles of Riemannian manifolds.

problem Investigate geometric properties of tangent bundles and their lifts.
method Analyze lift metrics and connections on TMTM of (M,g)(M,g), and study statistical and Codazzi couples.
result Prove a result on 11-Stein and Osserman structures on TMTM.

Study on constant curvature immersions of surfaces into flag manifolds.

problem Investigate constant curvature immersions of Riemann surfaces into flag manifolds.
method Investigate pseudoholomorphic maps and invariant metrics on flag manifolds.
result Unitarily equivalent primitive immersions of the two-sphere into full flag manifolds have constant curvature under all invariant metrics.

Optimal spectral initializers impact phase retrieval phase transitions.

problem Understanding the limits of phase retrieval algorithms.
method Developed Random duality theory (RDT) to characterize optimal spectral initializers.
result Optimal spectral initializers can fall into flat regions of the phase retrieval manifold, making phase retrieval difficult.

The study examines Bergman kernels on complex manifolds with boundary and their asymptotic expansions.

problem Analyzing Bergman kernels on complex manifolds with boundary and their asymptotic behavior.
method Establishing asymptotic expansions of partial Bergman kernels for high-frequency Fourier modes on R\mathbb{R}-symmetric complex manifolds with boundary.
result Established R\mathbb{R}-equivariant extension results for biholomorphic maps between weakly pseudoconvex domains.

We lift ambit fields as introduced by Barndorff-Nielsen and Schmiegel to a class of Hilbert space-valued volatility modulated Volterra processes. We name this class Hambit fields, and show that they can be expressed as a countable sum of weighted real-valued volatility modulated Volterra processes. Moreover, Hambit fie…

2015-09-28abs ↗pdf ↗

In this paper, we define a complete lift for semisprays. If SS is a semispray on a manifold MM, its complete lift is a new semispray ScS^c on TMTM. The motivation for this lift is two-fold: First, geodesics for ScS^c correspond to the Jacobi fields for SS, and second, this complete lift generalizes and unifies previ…

2008-09-08abs ↗pdf ↗

Geometric structures are lifted to higher tangent bundles preserving statistical properties.

problem Lifting statistical structures to higher tangent bundles while maintaining their properties.
method Natural lifts of geometric objects and potentials to higher tangent bundles, preserving statistical manifold structures.
result Lifted statistical structures on higher tangent bundles maintain pseudo-Riemannian metrics and are again statistical manifolds.

Study Weinstein structures on toric divisors' complements.

problem Understanding Weinstein structures on toric divisors' complements.
method Define a partially-centered condition on Delzant polytopes, develop an algorithm for Weinstein handlebody diagrams.
result Explicit Weinstein structures for complements of smoothed toric divisors.

In the present paper, we study complete and vertical lifts of tensor fields from a smooth manifold MM to its Weil bundle TAMT^A M defined by a Frobenius Weil algebra AA. For a Poisson manifold (M,w)(M,w), we show that the complete lift wCw^C and the vertical lift wVw^V of the Poisson tensor ww are Poisson tensors on $T^…

2009-07-31abs ↗pdf ↗

In this paper we continue to study equivariant pencil liftings and differential operators on the algebra of densities. We emphasize the role that the geometry of the extended manifold plays. Firstly we consider basic examples. We give a projective line of diff(MM)-equivariant pencil liftings for first order operators,…

2014-01-31abs ↗pdf ↗