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

88175263350 · Jun 202019922001200920172026
48 results for online regularization

Paper proposes a new dynamic pricing method with always-valid online statistical learning.

problem Designing dynamic pricing policies that adapt to online uncertainty and maintain validity.
method Regularized online statistical learning with theoretical guarantees and three major advantages.
result Proposed OORMLP pricing policy secures logarithmic regret in decision horizon.

Regularized online learning is widely used in machine learning applications. In online learning, performing exact minimization (i.e.,i.e., implicit update) is known to be beneficial to the numerical stability and structure of solution. In this paper we study a class of regularized online algorithms without linearizing the…

2018-09-25abs ↗pdf ↗

Paper develops an online learning algorithm for functional data models.

problem Recovering slope functions or predictors in functional data models.
method Online regularized learning algorithm in reproducing kernel Hilbert spaces with polynomially decaying step-size.
result Established fast convergence rates for estimation error without capacity assumption.

Adaptive online learning algorithm improves history forgetting in nonstationary environments.

problem Adversarial nonstationary environments where future data can be very different from past data.
method Discounted regret in online convex optimization, FTRL-based algorithm, adaptive learning rate.
result Improves classical gradient descent with constant learning rate in online convex optimization.

KL-regularized RL from expert demos can lead to slow, unstable learning.

problem Pathological training dynamics in KL-regularized RL from expert demonstrations.
method Empirical analysis and non-parametric behavioral reference policies.
result KL-regularized RL can be significantly improved by using non-parametric behavioral policies.

Improves online learning algorithms for functional models with capacity assumptions.

problem Convergence rates of online stochastic gradient descent algorithms for functional linear models.
method Characterizations of slope function regularity, kernel space capacity, and sampling process covariance operator.
result Capacity assumptions can alleviate saturation of convergence rates as function regularity increases.

Study on deleting user data in linear regression models to maintain limited memory.

problem Deleting user data in a limited time frame for statistical models.
method Proposed FIFD-OLS and FIFD-Adaptive Ridge algorithms for low-dimensional and online settings.
result Demonstrated effectiveness of FIFD-Adaptive Ridge in maintaining statistical efficiency.

New bounds for online portfolio selection without smoothness assumptions.

problem Online portfolio selection with non-Lipschitz, non-smooth losses.
method Data-dependent bounds using novel smoothness characterizations and FTRL with self-concordant regularizers.
result Achieves logarithmic regrets when data is 'easy' and sublinear worst-case regrets.

Study online learning in RKHS with dependent processes, focusing on \(β\)- and \(φ\)-mixing.

problem Online learning in RKHS with dependent data.
method Online regularized learning algorithm in RKHS, analyzing \(β\)- and \(φ\)-mixing sequences.
result Probabilistic upper bounds and convergence rates for mixing coefficients.

Unified framework for high-dimensional online learning with non-divergent error bounds and adaptive gains.

problem Divergence of error bounds in high-dimensional online learning as data batches increase.
method Asynchronous decomposition framework with summary statistics and dynamic regularization.
result Non-divergent error bounds and adaptive gains in sparse online optimization.

Improved online PCA algorithm learns from evolving norm of parameter vector.

problem Discarding evolving norm in online PCA leads to suboptimal learning.
method Implicitly Normalized Online PCA (INO-PCA) removes unit-norm constraint.
result Parameter norm evolution leads to improved learning behavior.

New algorithms adaptively compete against complex environments with local regularities.

problem Efficiently competing against complex, locally regular comparator functions in nonparametric settings.
method Locally-adaptive online algorithms using hierarchical εε-nets and tree experts.
result Proved regret bounds scaling with different types of local regularities, delivering better performance for simple profiles.

New online method for multivariate probabilistic electricity price forecasting.

problem Multivariate probabilistic forecasting of electricity prices.
method Online multivariate distributional regression with LASSO regularization.
result Robust and interpretable joint prediction intervals for 24-hour electricity prices.

In this paper, we study the online learning algorithm without explicit regularization terms. This algorithm is essentially a stochastic gradient descent scheme in a reproducing kernel Hilbert space (RKHS). The polynomially decaying step size in each iteration can play a role of regularization to ensure the generalizati…

2017-10-10abs ↗pdf ↗

Optimal bounds on regret and constraint violation in adversarial COCO.

problem Minimizing regret and cumulative constraint violation in adversarial COCO.
method New surrogate loss function and Follow-the-Regularized-Leader/Online Gradient Descent.
result Achieved optimal O(T)O(\sqrt{T}) bounds on both regret and cumulative constraint violation.

We propose a voted dual averaging method for online classification problems with explicit regularization. This method employs the update rule of the regularized dual averaging (RDA) method, but only on the subsequence of training examples where a classification error is made. We derive a bound on the number of mistakes…

2013-10-17abs ↗pdf ↗

Recently, a novel family of biologically plausible online algorithms for reducing the dimensionality of streaming data has been derived from the similarity matching principle. In these algorithms, the number of output dimensions can be determined adaptively by thresholding the singular values of the input data matrix. …

2016-12-11abs ↗pdf ↗

This work proposes robust reinforcement learning methods using both offline and online data.

problem Designing robust policies against parameter uncertainties in high-dimensional systems.
method Proposes RPQ for model-free learning with historical data and HyTQ for hybrid learning with both historical and online data.
result Unified analysis and theoretical guarantees for robust optimal policies in high-dimensional systems.

New method proves fast regret bounds for online RLHF with generalized preferences.

problem Minimizing max-regret in online RLHF with general preferences and bandit feedback.
method Adopted Generalized Bilinear Preference Model (GBPM) to investigate polylogarithmic regret guarantees.
result Proved polylogarithmic regret bounds for Greedy Sampling and Explore-Then-Commit policies under GBPM.

As application demands for online convex optimization accelerate, the need for designing new methods that simultaneously cover a large class of convex functions and impose the lowest possible regret is highly rising. Known online optimization methods usually perform well only in specific settings, and their performance…

2019-06-01abs ↗pdf ↗

New algorithm reduces regret in online portfolio and quantum state learning.

problem Efficiently learning portfolios and quantum states online with minimal regret.
method BISONS algorithm for online portfolio selection, SCHRODINGER'S BISONS for quantum states, with polylogarithmic regret.
result First efficient algorithm with polylogarithmic regret for online portfolio selection and quantum states.

We propose a version of least-mean-square (LMS) algorithm for sparse system identification. Our algorithm called online linearized Bregman iteration (OLBI) is derived from minimizing the cumulative prediction error squared along with an l1-l2 norm regularizer. By systematically treating the non-differentiable regulariz…

2012-10-01abs ↗pdf ↗

New algorithm reduces online logistic regression regret without exponential constant.

problem Improper learning in online logistic regression with logarithmic regret.
method Regularized empirical risk minimization with surrogate losses.
result Regret scaling as O(B log(Bn)) with low computational complexity.

MCNet improves uncertainty calibration in online advertising by modeling complex relations and balancing performance.

problem Lack of effective calibration for complex relations and context features in online advertising.
method Introduces MCNet with MCF, order-preserving, and field-balance regularizers.
result Superior performance in generating well-calibrated probability predictions on public and industrial datasets.

Improved online penalty selection for time series models.

problem Efficiently selecting penalty parameters for lasso in time series models.
method Enhanced autoregressive model with online penalty selection.
result Significantly improved computational performance and forecast accuracy.

This work establishes always-valid risk bounds for online matrix completion.

problem Challenges in establishing always-valid concentration inequalities for online matrix completion.
method Combines non-asymptotic martingale concentration and regularized low-rank matrix regression.
result Establishes always-valid risk bound process for online matrix completion.

New setup for continuous online learning improves understanding of imitation learning.

problem Challenges in capturing regularity in online problems.
method Continuous Online Learning (COL) setup, focusing on continuous gradient changes.
result Fundamental equivalence between sublinear dynamic regret and solving certain EPs.

Current online learning methods suffer issues such as lower convergence rates and limited capability to select important features compared to their offline counterparts. In this paper, a novel framework for online learning based on running averages is proposed. Many popular offline regularized methods such as Lasso, El…

2018-03-30abs ↗pdf ↗

We present an online approach to portfolio selection. The motivation is within the context of algorithmic trading, which demands fast and recursive updates of portfolio allocations, as new data arrives. In particular, we look at two online algorithms: Robust-Exponentially Weighted Least Squares (R-EWRLS) and a regulari…

2010-05-17abs ↗pdf ↗

Solving logistic regression with L1-regularization in distributed settings is an important problem. This problem arises when training dataset is very large and cannot fit the memory of a single machine. We present d-GLMNET, a new algorithm solving logistic regression with L1-regularization in the distributed settings. …

2014-11-24abs ↗pdf ↗

The paper analyzes SGD with dropout regularization in linear models, proving asymptotic properties and providing inference tools.

problem Analyzing the behavior of SGD with dropout regularization in linear models.
method Establishing geometric-moment contraction (GMC) and proving quenched central limit theorems (CLT).
result The existence of a unique stationary distribution and asymptotic normality results for SGD with dropout.

This work develops a unified framework for RLHF with general ff-divergence regularization.

problem Theoretical understanding of general ff-divergence regularization in RLHF.
method Holistic approach across ff-divergence class, two algorithms based on distinct sampling principles.
result Provably efficient algorithms with O(logT)O(\log T) regret and O(1/T)O(1/T) sub-optimality gap.

Deep learning is the state-of-the-art in fields such as visual object recognition and speech recognition. This learning uses a large number of layers and a huge number of units and connections. Therefore, overfitting is a serious problem with it, and the dropout which is a kind of regularization tool is used. However, …

2017-11-09abs ↗pdf ↗