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

115231346461 · Jun 202019922001200920172026
48 results for Continuity Guarantees

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.

Extends neural network approximations to guarantee continuity of real-world learning tasks.

problem Guaranteeing continuity of real-world learning tasks given by conditional expectations.
method Establishing conditions on learning tasks that guarantee their continuity under a factorization of the data-generating process.
result Conditions guaranteeing the continuity of practically any derived learning task.

OGD proves robustness to Catastrophic Forgetting in Continual Learning.

problem Catastrophic Forgetting in Continual Learning with deep neural networks.
method Theoretical framework based on Neural Tangent Kernel for OGD.
result First generalization bound for SGD and OGD in Continual Learning.

Algorithm generates private continuous-time data for sensitive domains.

problem Private generation of continuous-time data for sensitive domains.
method Mean-field Langevin dynamics and noisy particle gradient descent.
result Strong privacy guarantees for one-time data contributions.

This paper tackles discontinuous neural networks for better approximation of piecewise continuous functions.

problem Limitation of neural networks in approximating piecewise continuous functions due to discontinuities.
method Proposes a decoupled two-step procedure to train a discontinuous deep neural network model.
result Provides approximation guarantees for the proposed model in piecewise continuous function spaces.

DR-submodular continuous functions are important objectives with wide real-world applications spanning MAP inference in determinantal point processes (DPPs), and mean-field inference for probabilistic submodular models, amongst others. DR-submodularity captures a subclass of non-convex functions that enables both exact…

2017-11-04abs ↗pdf ↗

Study improves sample complexity for distinguishing continuous distributions and causal relationships.

problem Distinguishing continuous distributions and causal relationships in the presence of unobserved confounding.
method Proposed an estimator of KL divergence based on von Mises expansion for closeness testing.
result Established sample complexity guarantees for causal discovery in non-linear models with continuous variables and unobserved confounding.

The paper provides theoretical guarantees for behavior cloning using generative models.

problem Behavior cloning of complex expert demonstrations using generative models.
method The paper proposes a theoretical framework invoking low-level controllers to stabilize imitation around expert demonstrations. It shows that with suitable low-level stability guarantees and powerful generative models, pure supervised behavior cloning can match expert trajectories.
result The paper proves that with a suitable low-level stability guarantee and a powerful enough generative model, pure supervised behavior cloning can generate trajectories matching the per-time step distribution of essentially arbitrary expert trajectories in an optimal transport cost.

Efficient algorithms for contextual bandits with smooth regret in continuous action spaces.

problem Efficient learning in large or continuous action spaces.
method Smooth regret notion and efficient algorithms for general function approximation.
result Statistically and computationally efficient algorithms for contextual bandits with smooth regret.

The paper proposes a method to learn the structure of continuous-action games with non-parametric utilities using a limited number of samples.

problem Learning the exact structure of continuous-action games with non-parametric utility functions.
method An 1\ell_1 regularized method that encourages sparsity of the Fourier transform coefficients of the utility functions, accessed via a few Nash equilibria and their noisy utilities.
result The method recovers the exact structure of the utility functions and the game structure with provable theoretical guarantees.

RANDPOL uses randomized networks for efficient reinforcement learning in continuous state and action MDPs.

problem Efficient reinforcement learning in environments with continuous state and action spaces.
method RANDPOL uses randomized function approximation to represent policy and value functions, providing finite time guarantees and improved numerical performance.
result RANDPOL achieves better numerical performance and provides finite time guarantees compared to deep neural network based algorithms.

This paper tackles catastrophic forgetting in neural networks by providing a unified framework for regularization-based continual learning.

problem Catastrophic forgetting in neural networks trained sequentially on multiple tasks.
method Formulates regularization-based continual learning as a second-order Taylor approximation of the loss function, leading to a unified framework.
result Theoretical results indicate the importance of accurate approximation of the Hessian matrix for optimization and generalization.

The paper provides approximation guarantees for neural networks trained with gradient flow.

problem Approximating neural networks trained with gradient flow in continuous L2(Sd1)L_2(\mathbb{S}^{d-1})-norm.
method NTK argument for non-convex second but last layer, under-parametrized regime.
result Gradient flow convergence guarantees for neural networks under Sobolev smoothness assumptions.

Paper formalizes continual learning, proposing a feature extraction approach.

problem Learning from multiple environments without forgetting previous ones.
method Feature extraction framework and gradient-based algorithm DPGD.
result Efficient algorithm DPGD avoids catastrophic forgetting.

Study examines stability of image-reconstruction algorithms using variational regularization.

problem Stability and robustness of image-reconstruction algorithms in medical imaging.
method Review and novel stability results for p\ell_p-regularized linear inverse problems, focusing on p(1,)p\in(1,\infty).
result Guarantees Lipschitz continuity for small pp and Hölder continuity for larger pp in Lp(Ω)L_p(Ω) function spaces.

New insights into continual learning for deep models, showing convergence issues but local linear solutions.

problem Challenges in continual learning for homogeneous deep models.
method Sequential projections onto task margin sets, leveraging nonconvex projection theory.
result Local linear convergence under certain conditions for homogeneous deep networks.

Paper relaxes SGD privacy and generalization guarantees for non-smooth convex losses.

problem Privacy and generalization in SGD for non-smooth convex losses.
method Relaxes Lipschitz and strong smoothness assumptions to Hölder smoothness, proving (ε,δ)(ε,δ)-DP and optimal excess risk.
result Noisy SGD with αα-Hölder smooth losses achieves optimal excess risk with linear gradient complexity for α1/2α \geq 1/2.

New RBF networks can approximate any continuous function.

problem Approximating any continuous function on a compact subset.
method Replacing smoothing factors with shifts in RBF networks and proving approximation under certain conditions.
result RBF networks can approximate any continuous function on any compact subset.

Private CI tests for continuous Z with privacy constraints.

problem Testing conditional independence under differential privacy constraints.
method Developed two private CI testing procedures based on generalized covariance and conditional randomization tests.
result First private CI tests with rigorous theoretical guarantees for continuous Z.

Square-root natural-gradient improves variational inference convergence.

problem Challenges in establishing theoretical convergence guarantees for natural-gradient descent.
method Square-root parameterization for Gaussian covariance.
result Establishes novel convergence guarantees for natural-gradient Gaussian inference.

Neural Jump ODE improves continuous-time prediction and filtering of irregularly sampled time series.

problem Theoretical guarantees for continuous-time prediction and filtering of irregularly observed time series.
method Introducing Neural Jump ODE (NJ-ODE) that models conditional expectation between observations with neural ODEs and jumps.
result Theoretical guarantees for the L2L^2-optimal prediction are provided, showing convergence of model output to optimal prediction.

We consider a continuous map f:MNf :M\to N between two manifolds and try to estimate its multiplicity from below, i.e. find a qq-tuple of pairwise distinct points x1,...,xqMx_1,..., x_q\in M such that f(x1)=f(x2)=...=f(xq)f(x_1) = f(x_2) = ... = f(x_q). We show that there are certain characteristic classes of vector bundle fTNTMf^*TN-TM that guarant…

2010-02-03abs ↗pdf ↗

New method protects whistleblowers from retaliation by ensuring their reports remain private.

problem Whistleblowers face retaliation, and current protections are insufficient.
method Formalizes protection against strong-adversary threat model as per-report (0,δ)(0, δ)-differential privacy, and provides a generic mechanism to reduce private auditing to private continual counting.
result Demonstrates a reduction in selection error and improved utility over randomized response.

In this paper, we consider the problem of black box continuous submodular maximization where we only have access to the function values and no information about the derivatives is provided. For a monotone and continuous DR-submodular function, and subject to a bounded convex body constraint, we propose Black-box Contin…

2019-01-28abs ↗pdf ↗

New method improves submodular maximization for machine learning applications.

problem Inexact monotonicity in submodular functions limits traditional algorithms' performance.
method Introduces monotonicity ratio as a continuous version of monotonicity, leading to improved approximation guarantees.
result Improved approximation ratios for movie recommendation, quadratic programming, and image summarization.

Hypersolvers enable fast continuous-depth models for practical applications.

problem Infinite-depth models like Neural ODEs are computationally infeasible for large problems.
method Introducing hypersolvers, neural networks that solve ODEs efficiently with theoretical guarantees.
result Hypersolvers achieve comparable inference time to traditional discrete networks, making continuous-depth models practical.

Safe imitation learning with a safety layer for flexible training.

problem Flexible yet safe imitation learning for complex tasks.
method Theory and modular method with a safety layer for continuous policy, adversarial training, and worst-case safety guarantees.
result Robustness advantage of safety layer during training compared to test time.

We consider a family of learning strategies for online optimization problems that evolve in continuous time and we show that they lead to no regret. From a more traditional, discrete-time viewpoint, this continuous-time approach allows us to derive the no-regret properties of a large class of discrete-time algorithms i…

2014-01-27abs ↗pdf ↗

Stochastic optimization of continuous objectives is at the heart of modern machine learning. However, many important problems are of discrete nature and often involve submodular objectives. We seek to unleash the power of stochastic continuous optimization, namely stochastic gradient descent and its variants, to such d…

2017-11-05abs ↗pdf ↗

In this paper, we study fundamental problems of maximizing DR-submodular continuous functions that have real-world applications in the domain of machine learning, economics, operations research and communication systems. It captures a subclass of non-convex optimization that provides both theoretical and practical guar…

2019-09-25abs ↗pdf ↗

Improved Nyström approximation for kernel quadrature with theoretical guarantees.

problem Efficiently approximating positive definite kernels for large datasets.
method Refined sampling and subspace selection in Nyström approximation.
result Novel theoretical guarantees for non-i.i.d. landmark points in kernel quadrature.

Two algorithms create high-quality triangular meshes for surfaces with guaranteed angles.

problem Creating high-quality triangular meshes for surfaces with controlled angles.
method MidNormal and GradNormal algorithms generate meshes with specified angle constraints.
result Meshes converge to surfaces as mesh size decreases, maintaining specified angles.