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.
New filters match advanced composition for adaptive privacy, with practical constants.
In this paper, we present C-ADAM, the first adaptive solver for compositional problems involving a non-linear functional nesting of expected values. We proof that C-ADAM converges to a stationary point in with being a precision parameter. Moreover, we demonstrate the importance of our resul…
Paper simplifies DP composition for adaptive privacy budgets, enabling better privacy and accuracy in deep learning.
AdaGrad fails to adapt to Hölder-smoothness in composite optimization problems.
Adaptive sampling method solves constrained and composite optimization problems.
Adapts Altman's model to compositional data for bankruptcy prediction.
Adaptive MAB algorithms handle composite, anonymous feedback without reward interval knowledge.
OCEAN infers online task identities from context variables.
Paper improves privacy bounds for shuffle model using novel numerical techniques.
Enhances DGPs with adaptive RKHS Fourier features for better non-stationary pattern modeling.
Recently, much work has been done on extending the scope of online learning and incremental stochastic optimization algorithms. In this paper we contribute to this effort in two ways: First, based on a new regret decomposition and a generalization of Bregman divergences, we provide a self-contained, modular analysis of…
In this paper, we give a new construction of the adapted complex structure on a neighborhood of the zero section in the tangent bundle of a compact, real-analytic Riemannian manifold. Motivated by the "complexifier" approach of T. Thiemann as well as certain formulas of V. Guillemin and M. Stenzel, we obtain the polari…
New method improves RL/IL agents' adaptability to unseen environments.
CARE method estimates precision matrix for compositional data, achieving optimality in high dimensions.
Framework for lifelong learning of compositional structures.
New approach for open ad hoc teamwork using graph-based policy learning.
Energy-based models can generate complex images by combining simpler concepts.
We propose a new stochastic first-order algorithmic framework to solve stochastic composite nonconvex optimization problems that covers both finite-sum and expectation settings. Our algorithms rely on the SARAH estimator introduced in (Nguyen et al, 2017) and consist of two steps: a proximal gradient and an averaging s…
System learns to combine multiple model components for personalized text generation.
This paper addresses measurement errors in high-dimensional compositional data using a log-contrast model calibration approach.
BOIS optimizes complex systems by leveraging structural knowledge.
A new offline RL framework unifies imitation learning and vanilla offline RL.
Deep-HGP uses Bayesian nonparametric approach for complex data regression.
We propose an adaptive smoothing algorithm based on Nesterov's smoothing technique in \cite{Nesterov2005c} for solving "fully" nonsmooth composite convex optimization problems. Our method combines both Nesterov's accelerated proximal gradient scheme and a new homotopy strategy for smoothness parameter. By an appropriat…
New methods for predicting compositional data using conformal prediction.
A new privacy accountant for Gaussian differential privacy measures individual privacy losses.
In this work we introduce a new optimisation method called SAGA in the spirit of SAG, SDCA, MISO and SVRG, a set of recently proposed incremental gradient algorithms with fast linear convergence rates. SAGA improves on the theory behind SAG and SVRG, with better theoretical convergence rates, and has support for compos…
Paper proves multiplicative weight updates can train neural networks without learning rate tuning.
We consider first order gradient methods for effectively optimizing a composite objective in the form of a sum of smooth and, potentially, non-smooth functions. We present accelerated and adaptive gradient methods, called FLAG and FLARE, which can offer the best of both worlds. They can achieve the optimal convergence …
While statistics and machine learning offers numerous methods for ensuring generalization, these methods often fail in the presence of adaptivity---the common practice in which the choice of analysis depends on previous interactions with the same dataset. A recent line of work has introduced powerful, general purpose a…
We introduce a new notion of the stability of computations, which holds under post-processing and adaptive composition. We show that the notion is both necessary and sufficient to ensure generalization in the face of adaptivity, for any computations that respond to bounded-sensitivity linear queries while providing acc…
UCB-TQL learns from multiple tasks with shared dynamics and adapts to task-specific variations.
Extracting automatically the complex set of features composing real high-dimensional data is crucial for achieving high performance in machine--learning tasks. Restricted Boltzmann Machines (RBM) are empirically known to be efficient for this purpose, and to be able to generate distributed and graded representations of…
The CSA-ES is an Evolution Strategy with Cumulative Step size Adaptation, where the step size is adapted measuring the length of a so-called cumulative path. The cumulative path is a combination of the previous steps realized by the algorithm, where the importance of each step decreases with time. This article studies …
In this contribution we describe an approach to evolve composite covariance functions for Gaussian processes using genetic programming. A critical aspect of Gaussian processes and similar kernel-based models such as SVM is, that the covariance function should be adapted to the modeled data. Frequently, the squared expo…
HKRR adapts to MIM, overcoming the curse of dimensionality.
In this paper, we propose a unified view of gradient-based algorithms for stochastic convex composite optimization by extending the concept of estimate sequence introduced by Nesterov. This point of view covers the stochastic gradient descent method, variants of the approaches SAGA, SVRG, and has several advantages: (i…
The adaptive gradient online learning method known as AdaGrad has seen widespread use in the machine learning community in stochastic and adversarial online learning problems and more recently in deep learning methods. The method's full-matrix incarnation offers much better theoretical guarantees and potentially better…
Study develops efficient algorithm for probabilistic penetration response of composite plates.
The recent trend for acquiring big data assumes that possessing quantitatively more and qualitatively finer data necessarily provides an advantage that may be critical in competitive situations. Using a model complex adaptive system where agents compete for a limited resource using information coarse-grained to differe…
Unified framework controls false discovery rate in bandit multiple testing.
Geometry-aware KDE model improves multiclass quantification.
Logistic regression models are a popular and effective method to predict the probability of categorical response data. However inference for these models can become computationally prohibitive for large datasets. Here we adapt ideas from symbolic data analysis to summarise the collection of predictor variables into his…
RB-Modulation trains free diffusion models without external adapters.
In this paper we propose a new class of Dynamic Mixture Models (DAMMs) being able to sequentially adapt the mixture components as well as the mixture composition using information coming from the data. The information driven nature of the proposed class of models allows to exactly compute the full likelihood and to avo…
A new family of conformal test martingales based on Legendre polynomials for online exchangeability testing.
DNNs can learn complex functions efficiently by breaking the curse of dimensionality.
Motivated by big data applications, first-order methods have been extremely popular in recent years. However, naive gradient methods generally converge slowly. Hence, much efforts have been made to accelerate various first-order methods. This paper proposes two accelerated methods towards solving structured linearly co…