Adapts example weights to optimize black-box metrics.
problem Optimizing metrics defined by black-box functions.
method Adaptive example weighting and iterative post-shifting.
result Improves classification performance compared to baselines.
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.
168,694 papers · 148 categories
Trend · papers per month
48 results for “iterative post-shifting”
M-FISHER detects and adapts to streaming data shifts with statistical validity and stability.
problem Detecting and adapting to distributional shifts in streaming data.
method Constructs an exponential martingale from non-conformity scores and applies Ville's inequality for detection. Fisher-preconditioned updates for adaptation.
result Establishes M-FISHER as a principled approach for robust, anytime-valid detection and geometrically stable adaptation.
Study examines Indian equity mutual funds' investment style and risk-shifting.
problem Understanding how Indian equity mutual funds' investment styles affect their returns.
method Estimating size and style beta coefficients, identifying breakpoints, analyzing investment styles, and assessing risk-shifting intensity.
result Funds can enhance returns by shifting to high-return styles like Small Value and Small Blend.
A new method detects distribution shifts faster than existing CTMs.
problem Detecting distribution shifts in data streams with contamination issues.
method Uses a fixed reference dataset to compare each new sample, avoiding contamination.
result Detects distribution shifts faster and more reliably than standard CTMs.
Improving sparsity of deep neural networks (DNNs) is essential for network compression and has drawn much attention. In this work, we disclose a harmful sparsifying process called filter collapse, which is common in DNNs with batch normalization (BN) and rectified linear activation functions (e.g. ReLU, Leaky ReLU). It…
Bayesian framework estimates label shift for improved classifier performance.
problem Label shift in supervised learning leading to degraded classifier performance.
method Bayesian framework with dynamic Dirichlet priors and online EM algorithms.
result Significant improvements in classifier accuracy over state-of-the-art methods.
Paper analyzes iterates in high-dimensional linear models and proposes estimators for their generalization error.
problem Analyzing iterates in high-dimensional linear models with comparable feature and sample sizes.
method Novel estimators for generalization error, debiasing corrections, and valid confidence intervals.
result Estimators are -consistent and can be used for early stopping.
Paper analyzes iterative learning for concept classes and learns half-spaces.
problem Learning concept classes efficiently with iterative learners.
method Analyzes various settings of iterative learning and provides a constructive algorithm for half-spaces.
result Constructive iterative algorithm for learning half-spaces from informant.
WaveFit uses fixed-point iteration to create high-quality neural vocoders.
problem Creating high-quality neural vocoders with fast inference.
method Integrates GANs' adversarial training into a DDPM-like iterative framework based on fixed-point iteration.
result WaveFit synthesizes speech with naturalness comparable to human speech, and is significantly faster than existing methods.
In this paper, we introduce the notions of an iterated planar Lefschetz fibration and an iterated planar open book decomposition and prove the Weinstein conjecture for contact manifolds supporting an open book that has iterated planar pages. For , we show that a -dimensional contact manifold suppor…
We prove that an iterated torus knot type fails the uniform thickness property (UTP) if and only if all of its iterations are positive cablings, which is precisely when an iterated torus knot type supports the standard contact structure. We also show that all iterated torus knots that fail the UTP support cabling knot …
Sharp analysis of power iteration for tensor PCA, improving convergence and stopping criteria.
problem Analyzing the power iteration algorithm for tensor PCA to improve convergence and stopping criteria.
method Sharp bounds on the number of iterations, revealing a smaller algorithmic threshold, proposing a stopping criterion.
result Sharp bounds on the number of iterations required for power method to converge, revealing a smaller algorithmic threshold than previously conjectured.
We deduce from the work of Chen, that the restriction morphism from closed free iterated integrals to closed iterated integrals on loops is onto. We use this to show that the module of higher order invariants of smooth functions is generated by free closed iterated integrals.
In this paper we study the smooth convex-concave saddle point problem. Specifically, we analyze the last iterate convergence properties of the Extragradient (EG) algorithm. It is well known that the ergodic (averaged) iterates of EG converge at a rate of (Nemirovski, 2004). In this paper, we show that the last…
Adaptive optimal control of nonlinear dynamic systems with deterministic and known dynamics under a known undiscounted infinite-horizon cost function is investigated. Policy iteration scheme initiated using a stabilizing initial control is analyzed in solving the problem. The convergence of the iterations and the optim…
An iterative SE(3)-Transformer model is developed for graph data.
problem Manipulating three-dimensional data with rotational and translational symmetries.
method Iterative SE(3)-equivariant attention mechanism applied to graph data.
result Iterative SE(3)-Transformer outperforms single-pass version on a toy problem.
Iterative method learns unknown constraints for MPC control.
problem Learning to satisfy unknown polyhedral state constraints in iterative MPC.
method Collects and improves estimates of unknown constraints using collected data, designs an MPC controller to satisfy the estimated constraints.
result Robust and probabilistic guarantees of constraint satisfaction as a function of task iterations.
Value iteration is a fixed point iteration technique utilized to obtain the optimal value function and policy in a discounted reward Markov Decision Process (MDP). Here, a contraction operator is constructed and applied repeatedly to arrive at the optimal solution. Value iteration is a first order method and therefore …
Iterates towards Kähler metrics with constant scalar curvature.
problem Finding constant scalar curvature Kähler metrics.
method Ricci iteration sequence of Rubinstein discretizing the pseudo-Calabi flow.
result The iteration sequence converges to a constant scalar curvature Kähler metric.
We give short proofs of the following two facts: Iterated principal circle bundles are precisely the nilmanifolds. Every iterated circle bundle is almost flat, and hence diffeomorphic to an infranilmanifold.
Algorithm recovers causal graphs from data with fewer tests.
problem Recovering causal graphs from observational data with latent confounders and selection bias.
method Iterative CI tests with increasing condition set sizes.
result Significantly fewer CI tests and condition sets compared to FCI.
Spherical T-duality for iterated sphere bundles
problem T-duality for iterated sphere bundles
method Repackaging cohomological data into Massey products
result Found T-dual iterated sphere bundles associated to Massey products
In this paper we investigate what kind of manifolds arise as the total spaces of iterated -bundles. A real Bott tower studied in \cite{CMO}, \cite{KM} and \cite{KN} is an example of an iterated -bundle. We show that the total space of an iterated -bundle is homeomorphic to an infra-nilmanifold. A real Bo…
Improved generalization with iterate averaging and adaptive algorithms.
problem Enhancing model generalization performance in high-dimensional settings.
method Gaussian process perturbation model, combine IA with large learning rates and regularisation, less frequent averaging, adaptive gradient methods.
result Iterate averaging with adaptive algorithms significantly outperforms SGD on various datasets.
DSPI connects natural policy gradient to policy iteration, proving global convergence.
problem Optimizing policies in reinforcement learning.
method DSPI framework, combining smoothed policy iteration and natural policy gradient.
result DSPI achieves geometric convergence and optimal complexity for policy optimization.
Strong stability of ergodic iterations proven without ergodic driving sequence.
problem Ensuring strong stability of ergodic iterations under non-ergodic driving sequences.
method Revisiting processes driven by stationary ergodic sequences, proving strong stability under mild conditions on recursive maps.
result Strong stability of iterations proven without ergodic driving sequence.
Policy iteration is a family of algorithms that are used to find an optimal policy for a given Markov Decision Problem (MDP). Simple Policy iteration (SPI) is a type of policy iteration where the strategy is to change the policy at exactly one improvable state at every step. Melekopoglou and Condon [1990] showed an exp…
New convergence rates for shuffling gradient methods without strong convexity.
problem Theoretical gap between shuffling gradient methods' empirical success and established convergence rates.
method Proved last-iterate convergence rates for shuffling gradient methods using function value gap.
result First last-iterate convergence rates for shuffling gradient methods without strong convexity.
Paper refutes conjecture on tensor power iteration convergence in overcomplete models.
problem Understanding convergence of tensor power iteration in overcomplete random tensors.
method Analysis of tensor power iteration dynamics from random initialization.
result Polynomially many steps are necessary for convergence, refutes logarithmic conjecture.
We study iteration maps of recurrence relations arising from mutation periodic quivers of arbitrary period. Combining tools from cluster algebra theory and (pre)symplectic geometry, we show that these cluster iteration maps can be reduced to symplectic maps on a lower dimensional submanifold, provided the matrix repres…
We bound the index of a subgroup in iterated Kodaira fibrations.
problem Bounding the index of a subgroup in iterated Kodaira fibrations.
method Passing to a finite index subgroup of π_1(X) to achieve the desired structure.
result We provide a bound on the index of such a group.
The Ricci iteration is a discrete analogue of the Ricci flow. We give the first study of the Ricci iteration on a class of Riemannian manifolds that are not Kähler. The Ricci iteration in the non-Kähler setting exhibits new phenomena. Among them is the existence of so-called ancient Ricci iterations. As we show, these …
We study the Ricci iteration for homogeneous metrics on spheres and complex projective spaces. Such metrics can be described in terms of modifying the canonical metric on the fibers of a Hopf fibration. When the fibers of the Hopf fibration are circles or spheres of dimension 2 or 7, we observe that the Ricci iteration…
Last SGD iterate bounds for overparameterized linear regression.
problem Analyzing the last iterate risk bounds of SGD with decaying stepsize for overparameterized linear regression.
method Problem-dependent analysis of last iterate risk bounds of SGD with geometrically decaying stepsize.
result Proved nearly matching upper and lower bounds on the excess risk for last iterate SGD with geometrically decaying stepsize.
We consider the infinite-horizon discounted optimal control problem formalized by Markov Decision Processes. We focus on several approximate variations of the Policy Iteration algorithm: Approximate Policy Iteration, Conservative Policy Iteration (CPI), a natural adaptation of the Policy Search by Dynamic Programming a…
Chen's iterated integrals are treated within synthetic differential geometry. The main result is that iterated integrals produce a subcomplex of the de Rham complex on the free path space as well as based path spaces.
We give a definition of higher dimensional iterated integrals based on integration over membranes. We prove basic properties of this definition and formulate a conjecture which extends Chen's de Rham Theorem for iterated integrals to the membrane case.
LocalKMeans parallelizes Lloyd's algorithm for distributed data.
problem Efficiently clustering data across multiple machines.
method Parallel local iterations with synchronization every L steps.
result Higher required signal-to-noise ratio due to local steps.
We develop a class of integrals on a manifold M called exponential iterated integrals, an extension of K. T. Chen's iterated integrals. It is shown that the matrix entries of any upper triangular representation of the fundamental group of M can be expressed via these new integrals. The ring of exponential iterated inte…
A well-known issue of Batch Normalization is its significantly reduced effectiveness in the case of small mini-batch sizes. When a mini-batch contains few examples, the statistics upon which the normalization is defined cannot be reliably estimated from it during a training iteration. To address this problem, we presen…
Last-iterate guarantees for learning in co-coercive games under noisy feedback.
problem Learning in co-coercive games with noisy feedback.
method Vanilla stochastic gradient descent with a new noise model.
result Last-iterate bound of order for co-coercive games.
Improved matching for multiple objects using a novel reweighting method.
problem Current multi-object matching methods have limitations and are not robust.
method Proposes a novel iterative reweighting strategy using the graph connection Laplacian.
result Demonstrates superior performance over state-of-the-art methods.
Iterative method 'Concent' corrects spectrum bias in covariance matrices.
problem Consistent bias in the spectrum of covariance matrices.
method 'Concent' iterative algorithm.
result Corrects spectrum bias for small and moderate dimensions.
OptEx accelerates first-order optimization with parallelized iterations.
problem Inefficiencies in first-order optimization algorithms for complex tasks.
method Approximately parallelized iterations using kernelized gradient estimation.
result OptEx achieves substantial efficiency improvements with an effective acceleration rate of .
In a recent series of papers it has been established that variants of Gradient Descent/Ascent and Mirror Descent exhibit last iterate convergence in convex-concave zero-sum games. Specifically, \cite{DISZ17, LiangS18} show last iterate convergence of the so called "Optimistic Gradient Descent/Ascent" for the case of \t…
Developed an efficient iterative algorithm for SVI model.
problem SVI model's optimizer's strong dependence on input starting point.
method Fixed-point and least-square optimizer.
result Convergence results for fixed-point iterative algorithm in certain situations.
New method speeds up distributed linear regression.
problem Efficiently solve distributed linear regression problems.
method Iteratively Pre-conditioned Stochastic Gradient Descent (IPSG)
result Converges linearly in expectation to the solution.
New iterative method solves Yamabe problem on small domains.
problem Solving Yamabe equation on small Riemannian domains.
method Iterative scheme to solve Yamabe equation without functional minimization.
result Solves Yamabe equation on small domains with constant scalar curvature.