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

1345 · Feb 202319922001200920172026
48 results for best-of-both-worlds

New algorithm achieves best-of-both-worlds performance in various online learning settings.

problem Achieving optimal performance in both adversarial and stochastic online learning settings.
method General reduction from best-of-both worlds to FTRL and OMD algorithms.
result Transformed existing algorithms into new ones with best-of-both-worlds guarantees.

New algorithm reduces regret in both adversarial and stochastic contexts.

problem Contextual combinatorial semi-bandits with adversarial and corrupted stochastic regimes.
method Follow-the-Regularized-Leader (FTRL) framework with Shannon entropy regularizer, accelerated by Karush-Kuhn-Tucker conditions.
result Achieves O~(T)\widetilde{\mathcal{O}}(\sqrt{T}) regret in adversarial and O~(lnT)\widetilde{\mathcal{O}}(\ln T) regret in corrupted stochastic regimes.

FTPL policy achieves best-of-both-worlds regret in decoupled bandits with reduced computational cost.

problem Decoupled multi-armed bandit problem with observed and unobserved losses.
method Follow-the-Perturbed-Leader (FTPL) policy that avoids convex optimization and resampling.
result Achieves constant regret in stochastic regime and optimal O(KT)O(\sqrt{KT}) regret in adversarial regime.

Develops a Best-of-Both-Worlds algorithm for linear contextual bandits with Tsallis entropy.

problem Linear contextual bandits with i.i.d. contexts.
method Follow-The-Regularized-Leader (FTRL) with Tsallis entropy.
result Achieves $O\left(\log(T)^{\frac{1+β}{2+β}}T^{\frac{1}{2+β}} ight)$ regret under margin condition.

New algorithm handles delayed feedback robustly, reducing regret without knowing delay bounds.

problem Bandits with variably delayed feedback, especially excessive delays.
method Implicit exploration scheme, adaptive skipping, drifted regret control.
result Can tolerate arbitrary excessive delays up to order T, reducing regret.

This paper improves FTPL algorithm for semi-bandit problems with best-of-both-worlds guarantees.

problem Optimizing regret in adversarial and stochastic mm-set semi-bandit problems.
method Extending FTPL with geometric resampling (GR) to mm-set semi-bandits and analyzing its performance.
result FTPL with Fréchet and Pareto distributions achieves O(mdT)O(\sqrt{mdT}) regret in adversarial setting and logarithmic regret in stochastic setting.

Develops model selection for bandits balancing adversarial and stochastic guarantees.

problem Model selection in bandit scenarios with simultaneous adversarial and stochastic high-probability regret.
method Nested policy classes, balanced candidate regret bounds, mis-specification tests.
result Best of both world guarantees in linear bandits with simultaneous adversarial and stochastic environments.

New adaptive learning rate improves FTRL's adaptivity to sparsity, game-dependency, and best-of-both-worlds.

problem Improving adaptivity in sequential decision-making problems.
method Developed a stability-penalty-adaptive (SPA) learning rate for FTRL.
result First BOBW algorithm with sparsity-dependent bound.

FTPL with Fréchet perturbation achieves near optimal regret bounds for m-set semi-bandit problems.

problem Optimizing regret bounds for m-set semi-bandit problems in adversarial and stochastic settings.
method Follow-the-Perturbed-Leader (FTPL) with Fréchet perturbation.
result Achieves near optimal regret bounds of O(nm(dlog(d)+m5/6))\mathcal{O}(\sqrt{nm}(\sqrt{d\log(d)}+m^{5/6})) in adversarial setting and logarithmic regret in stochastic setting.

New adaptive learning rate for FTRL reduces regret to Θ(T^2/3).

problem Minimax regret of Θ(T^2/3) in online learning.
method Adaptive learning rate framework matching stability, penalty, and bias terms.
result Improves Best-of-Both-Worlds (BOBW) regret upper bounds.

Algorithm learns both stochastic and adversarial MDPs with best-of-both-worlds guarantees.

problem Learning episodic MDPs with known transition and bandit feedback.
method Follow-the-Regularized-Leader method with a hybrid regularizer.
result Achieves O(logT)\mathcal{O}(log T) regret for stochastic losses and ildeO(T) ilde{\mathcal{O}}(\sqrt{T}) regret for adversarial losses.

New framework handles online decisions with replenishable resources, improving both adversarial and stochastic performance.

problem Online decision-making with resource constraints that can be replenished.
method Best-of-both-worlds primal-dual template for online learning problems with replenishment.
result First positive results for adversarial inputs and an instance-independent regret bound for stochastic inputs.

Improved FTRL algorithm for multi-armed bandits with various regularizers and multiple optimal arms.

problem Designing adaptive multi-armed bandit algorithms that perform optimally in both stochastic and adversarial settings.
method Follow-the-Regularized-Leader (FTRL) algorithm with a broad family of regularizers and a new learning rate schedule.
result Uniqueness of optimal arm assumption is unnecessary for FTRL with a broad family of regularizers.

Adaptive learning rate improves FTRL's performance in online learning.

problem Optimizing FTRL's learning rate for competitive regret in online learning.
method Formulated as a sequential decision-making problem, introduced competitive analysis framework, and proposed stability-penalty matching update rules.
result Achieved a constant competitive ratio under specific conditions, enabling Best-Of-Both-Worlds algorithms.

This paper proposes a Hilbert space embedding for Dirichlet Process mixture models via a stick-breaking construction of Sethuraman. Although Bayesian nonparametrics offers a powerful approach to construct a prior that avoids the need to specify the model size/complexity explicitly, an exact inference is often intractab…

2012-10-16abs ↗pdf ↗

New algorithms reduce regret in both stochastic and adversarial partial monitoring problems.

problem Partial monitoring with kk-actions and dd-outcomes.
method Follow-the-regularized-leader framework, exploration by optimization, adaptive learning rate.
result Best-of-both-worlds algorithms with favorable regret bounds in stochastic and adversarial settings.

How to reconcile the classical Heston model with its rough counterpart? We introduce a lifted version of the Heston model with n multi-factors, sharing the same Brownian motion but mean reverting at different speeds. Our model nests as extreme cases the classical Heston model (when n = 1), and the rough Heston model (w…

2018-10-11abs ↗pdf ↗

Paper optimizes FTPL for adversarial and stochastic bandits with specific tail distributions.

problem Optimizing Follow-the-Perturbed-Leader (FTPL) policy for bandit problems.
method Analyzes FTPL with Fréchet-type tail distributions in adversarial and stochastic settings.
result FTPL with certain Fréchet-type tail distributions achieves O(KT)\mathcal{O}(\sqrt{KT}) regrets in adversarial bandits.

We present a dual subspace ascent algorithm for support vector machine training that respects a budget constraint limiting the number of support vectors. Budget methods are effective for reducing the training time of kernel SVM while retaining high accuracy. To date, budget training is available only for primal (SGD-ba…

2018-06-26abs ↗pdf ↗

Advances FTPL results for bandit problems with unbounded perturbations.

problem Improving analytical foundations of FTPL in bandit problems.
method Revisiting classical FTRL-FTPL duality for unbounded perturbations.
result Establishes Best-of-Both-Worlds (BOBW) results for FTPL under a broad family of asymmetric unbounded perturbations.

Deep learning uses layers of transformations to predict structured data with uncertainty.

problem Predicting structured high-dimensional data efficiently and with uncertainty.
method Applying layers of semi-affine input transformations to find features for probabilistic statistical methods.
result Achieves scalable prediction rules with uncertainty quantification and feature selection.

Variational Bayesian inference and (collapsed) Gibbs sampling are the two important classes of inference algorithms for Bayesian networks. Both have their advantages and disadvantages: collapsed Gibbs sampling is unbiased but is also inefficient for large count values and requires averaging over many samples to reduce …

2012-06-13abs ↗pdf ↗

We consider active learning with logged data, where labeled examples are drawn conditioned on a predetermined logging policy, and the goal is to learn a classifier on the entire population, not just conditioned on the logging policy. Prior work addresses this problem either when only logged data is available, or purely…

2018-02-25abs ↗pdf ↗

Long Short-Term Memory (LSTM) is one of the most powerful sequence models. Despite the strong performance, however, it lacks the nice interpretability as in state space models. In this paper, we present a way to combine the best of both worlds by introducing State Space LSTM (SSL) models that generalizes the earlier wo…

2017-11-30abs ↗pdf ↗

Recent advances in stochastic gradient variational inference have made it possible to perform variational Bayesian inference with posterior approximations containing auxiliary random variables. This enables us to explore a new synthesis of variational inference and Monte Carlo methods where we incorporate one or more s…

2014-10-23abs ↗pdf ↗

New algorithm optimizes dueling bandits for both stochastic and adversarial preferences.

problem Optimizing decision-making in environments where only relative preferences are observed.
method Proposed a reduction from dueling bandits to multi-armed bandits, achieving optimal regret bounds.
result First best-of-both-world result for dueling bandits, optimal regret bound for Condorcet-winner benchmark.

Learning representations of nodes in a low dimensional space is a crucial task with many interesting applications in network analysis, including link prediction and node classification. Two popular approaches for this problem include matrix factorization and random walk-based models. In this paper, we aim to bring toge…

2019-09-08abs ↗pdf ↗

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 …

2016-05-26abs ↗pdf ↗

New theory sharpens Q-learning with LDTZ rate, proving it's best of both worlds.

problem Improving Q-learning's theoretical and practical performance.
method Developed a sharp non-asymptotic error bound and central limit theory for Q-learning with PD2Z-ν schedule.
result Q-learning with LDTZ schedule achieves rapid decay and asymptotic convergence guarantees.

Develops a strategy to minimize loss in both stochastic and adversarial environments for linear contextual bandits.

problem Linear contextual bandits with adversarial corruption.
method Proposes a novel strategy called Best-of-Both-Worlds (BoBW) RealFTRL, extending RealLinExp3 and FTRL.
result Regret upper bound of $O\left(\min\left\{\frac{(\log(T))^3}{Δ_{*}} + \sqrt{\frac{C(\log(T))^3}{Δ_{*}}},\ \ \sqrt{T}(\log(T))^2 ight\} ight)$, showing effectiveness in both stochastic and adversarial environments.

Neural Architecture Search has shown potential to automate the design of neural networks. Deep Reinforcement Learning based agents can learn complex architectural patterns, as well as explore a vast and compositional search space. On the other hand, evolutionary algorithms offer higher sample efficiency, which is criti…

2018-11-24abs ↗pdf ↗

Deep reinforcement learning (RL) methods generally engage in exploratory behavior through noise injection in the action space. An alternative is to add noise directly to the agent's parameters, which can lead to more consistent exploration and a richer set of behaviors. Methods such as evolutionary strategies use param…

2017-06-06abs ↗pdf ↗

Effectively combining logic reasoning and probabilistic inference has been a long-standing goal of machine learning: the former has the ability to generalize with small training data, while the latter provides a principled framework for dealing with noisy data. However, existing methods for combining the best of both w…

2019-06-05abs ↗pdf ↗

PPG separates policy and value function training phases for better reinforcement learning efficiency.

problem Challenges in traditional reinforcement learning methods for policy and value function optimization.
method Integrates Phasic Policy Gradient framework that splits policy and value function training into distinct phases.
result Significantly improves sample efficiency on Procgen Benchmark compared to PPO.

New optimization method combines gradient clipping and non-Euclidean smoothness.

problem Improving optimization in non-Euclidean spaces for machine learning.
method Hybrid of steepest descent and conditional gradient, incorporating weight decay.
result Achieves optimal convergence rate and demonstrates effectiveness in deep learning.

A new method optimizes a generalized Kullback-Leibler divergence for better simulation-based inference.

problem Optimizing likelihood functions when they are only known implicitly.
method Optimizes a generalized Kullback-Leibler divergence that accounts for normalization constants in unnormalized distributions.
result Unified approach that combines Neural Posterior Estimation and Neural Ratio Estimation.

We study the problem of off-policy value evaluation in reinforcement learning (RL), where one aims to estimate the value of a new policy based on data collected by a different policy. This problem is often a critical step when applying RL in real-world problems. Despite its importance, existing general methods either h…

2015-11-11abs ↗pdf ↗

One important partition of algorithms for controlling the false discovery rate (FDR) in multiple testing is into offline and online algorithms. The first generally achieve significantly higher power of discovery, while the latter allow making decisions sequentially as well as adaptively formulating hypotheses based on …

2019-10-11abs ↗pdf ↗