New method achieves both universality and adaptivity in online convex optimization.
problem Achieve optimal regret guarantees without prior knowledge of function curvature.
method Introduces UniGrad, a novel approach that achieves both universality and adaptivity.
result Achieves universal regret guarantees that adapt to gradient variation.
Survey of universal portfolio techniques for minimizing investment regret.
problem Minimizing investment regret in algorithmic trading.
method Explains various universal portfolio techniques and their proofs.
result Coverage of fundamental concepts and algorithms in regret minimization.
Universal online optimization for dynamic environments using uniclass prediction.
problem Online optimization in changing environments with dynamic regret.
method Reduces dynamic online optimization to uniclass prediction problem, allowing control over dynamic regret bounds.
result First paper with state-of-the-art dynamic regret guarantees for general convex cost functions.
The paper derives a new theorem for predicting batches of data.
problem Finding lower bounds on minimal batch regret.
method Derives a conditional version of the regret-capacity theorem.
result Reveals a connection between conditional Rényi divergence and conditional Sibson's mutual information.
New method evaluates LLMs fairness in universal prediction.
problem Evaluating fairness of large language models in universal prediction.
method Introducing batch regret as a modification of average regret for LLMs.
result Asymptotical value of batch regret for add-constant predictors on memoryless and first-order Markov sources.
To deal with changing environments, a new performance measure -- adaptive regret, defined as the maximum static regret over any interval, was proposed in online learning. Under the setting of online convex optimization, several algorithms have been successfully developed to minimize the adaptive regret. However, existi…
Paper shows how online betting algorithms' regret can be used to create tight confidence sequences.
problem Estimating the expectation of random variables from samples and creating time-uniform confidence sequences.
method Converts the regret guarantee of universal portfolio algorithms into time-uniform concentration inequalities and confidence sequences.
result Numerically obtained confidence sequences are never vacuous and satisfy the law of iterated logarithm.
Universal preconditioning reduces sequential prediction regret.
problem Improving sequential prediction performance.
method Convolve target sequence with orthogonal polynomial coefficients.
result First sublinear and hidden-dimension-independent regret bounds.
Lazy Gradient Descent outperforms existing polytope algorithms in pseudo-regret.
problem Achieving optimal regret bounds on polytopes efficiently.
method Lazy Online Gradient Descent on polytopes.
result Proves O ( 1 ) O(1) O ( 1 ) pseudo-regret against i.i.d opponents. We study the decades-old problem of online portfolio management and propose the first algorithm with logarithmic regret that is not based on Cover's Universal Portfolio algorithm and admits much faster implementation. Specifically Universal Portfolio enjoys optimal regret O ( N ln T ) \mathcal{O}(N\ln T) O ( N ln T ) for N N N financial instrum…
Improves bandit convex optimization with gradient variations.
problem Bandit Convex Optimization with Gradient Variations.
method Refined analysis of non-consecutive gradient variation.
result Improved dimension dependence for convex and strongly convex functions.
We show that the Subgradient algorithm is universal for online learning on the simplex in the sense that it simultaneously achieves O ( N ) O(\sqrt N) O ( N ) regret for adversarial costs and O ( 1 ) O(1) O ( 1 ) pseudo-regret for i.i.d costs. To the best of our knowledge this is the first demonstration of a universal algorithm on the simplex tha…
Develops a new method for online conformal prediction without manual tuning.
problem Achieving long-run 1 − α 1-α 1 − α coverage for arbitrary data streams in an informative manner. method Linearized regret theory and universal portfolio algorithms.
result Strong finite-time bounds on miscoverage for UP-OCP, outperforming prior methods.
In this paper, we study adaptive online convex optimization, and aim to design a universal algorithm that achieves optimal regret bounds for multiple common types of loss functions. Existing universal methods are limited in the sense that they are optimal for only a subclass of loss functions. To address this limitatio…
Algorithm minimizes regret in multi-criteria bandits with constraints.
problem Optimize primary attribute while respecting secondary constraints.
method Con-LCB algorithm that guarantees logarithmic regret and feasibility identification.
result Logarithmic regret and feasibility identification with high probability.
Algorithm finds optimal regularizers for online linear optimization.
problem Finding optimal regularizers to minimize regret in online linear optimization.
method Algorithm takes input sets and outputs an optimal regularizer for FTRL.
result Algorithm guarantees regret within a constant factor of the best possible learning algorithm.
New betting strategy reduces regret to ln(ln n) with protection against adversarial data.
problem Tackles the problem of minimizing regret in betting against adversarial and stochastic data.
method Combines insights from Robbins and Cover, using a mixture strategy.
result Exhibits a regret of O(ln(ln n)) on almost all paths, with O(log n) regret on the complement.
The paper optimizes regret using covariance between costs and decisions.
problem Optimizing expected regret in decision-making problems.
method Developed derivative theory of covariance regret functional, derived Gâteaux derivative, and extended to constrained optimization.
result Gradient of covariance regret is the cost covariance matrix, with implications for portfolio optimization.
The Predictive Normalized Maximum Likelihood (pNML) scheme has been recently suggested for universal learning in the individual setting, where both the training and test samples are individual data. The goal of universal learning is to compete with a ``genie'' or reference learner that knows the data values, but is res…
ERTS uses Thompson sampling for Gaussian entropic risk bandits, achieving regret bounds.
problem Risk in decision making complicates reward maximization in MAB problems.
method ERTS (Entropic Risk Thompson Sampling) using Thompson sampling with an entropic risk measure.
result Regret bounds for ERTS under entropic risk measure provided.
New algorithm minimizes expert selection regret in partial bandit feedback.
problem Minimizing expert selection regret in partial bandit feedback.
method Develops a sequential minimax optimal algorithm for a generalized partial monitoring setting.
result Second order regret bounds against a general expert selection sequence.
Generalized algorithm for translation and scale-invariant prediction.
problem Sequential prediction with expert advice, focusing on translation and scale invariance.
method Designing a generalized online algorithm using the universal prediction perspective to compete against a generic class of expert selection strategies.
result No preliminary knowledge of loss sequences is required; performance bounds are stable under arbitrary scalings and translations.
New algorithms minimize dynamic regret for strongly convex losses.
problem Minimizing dynamic regret for strongly convex losses.
method Developed Strongly Adaptive algorithms exploiting KKT conditions.
result Achieved near optimal dynamic regret of O ( d 1 / 3 n 1 / 3 e x t T V [ u 1 : n ] 2 / 3 ∨ d ) O(d^{1/3} n^{1/3} ext{TV}[u_{1:n}]^{2/3} \vee d) O ( d 1/3 n 1/3 e x t T V [ u 1 : n ] 2/3 ∨ d ) . A universal framework for constructing confidence sets using sequential likelihood mixing.
problem Constructing reliable confidence sets for realizable likelihood functions.
method Sequential likelihood mixing, integrating Bayesian inference and regret inequalities.
result Establishes fundamental connections and provable coverage guarantees for various inference techniques.
Universal algorithm learns unknown distribution for various decision-making problems.
problem Various statistical measures in contextual sequential decision-making.
method Infinite-dimensional functional regression oracle for cumulative distribution functions.
result Utility regret rate bounded by polynomial decay of eigenvalue sequence.
The paper proves a regret bound for a sub-Gaussian mixture on unbounded data.
problem Tackles the challenge of achieving regret bounds for sub-Gaussian mixtures on unbounded data.
method Uses path-wise (deterministic) regret bounds and a cumulative variance process to derive the bound.
result Shows that on a specific event, the regret is eventually bounded by ln(ln V_T).
New algorithms minimize dynamic regret in non-stationary online learning.
problem Universal dynamic regret minimization under exp-concave and smooth losses.
method Strongly Adaptive algorithms with a path variational based on second order differences of the comparator sequence.
result Achieve a dynamic regret of i l d e O ( d 2 n 1 / 5 C n 2 / 5 ∨ d 2 ) ilde O(d^2 n^{1/5} C_n^{2/5} \vee d^2) i l d e O ( d 2 n 1/5 C n 2/5 ∨ d 2 ) , optimal modulo dependencies. 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.
Faster algorithm reduces contextual bandit regret with fewer offline regression calls.
problem Optimizing reward in contextual bandits with unknown functions.
method Designing a simple algorithm with O ( log T ) {O}(\log T) O ( log T ) offline regression calls. result Achieves statistically optimal regret with minimal offline calls.
Algorithm provides online learning guarantees against general comparators in full and bandit feedback.
problem Adversarial online learning with data-dependent regret guarantees.
method Completely online algorithm with data-dependent regret guarantees for full and bandit feedback.
result Algorithm achieves expected performance against arbitrary comparator sequences in full and bandit feedback settings.
We consider a budget-constrained bandit problem where each arm pull incurs a random cost, and yields a random reward in return. The objective is to maximize the total expected reward under a budget constraint on the total cost. The model is general in the sense that it allows correlated and potentially heavy-tailed cos…
Bayesian bandit algorithms with approximate inference improve regret bounds in stochastic linear bandits.
problem Theoretical justification for Bayesian bandit algorithms with approximate inference in stochastic linear bandits.
method Proposed a theoretical framework to analyze approximate inference impact and conducted frequentist regret analysis on LinTS and LinBUCB.
result LinTS and LinBUCB preserve their original regret upper bounds with larger constant terms in approximate inference settings.
New findings on universal learning in contextual bandits with adversarial rewards.
problem Learning in contextual bandits with time-varying, adversarial rewards.
method Characterization of learnable processes and necessary/sufficient conditions for universal learning.
result Optimistic universal learning for contextual bandits with adversarial rewards is impossible in general.
Improved regret bounds for DP-KLUCB and DP-IMED in Bernoulli bandits.
problem Minimizing regret in stochastic bandits under ε-global Differential Privacy.
method Developed DP versions of KLUCB and IMED, proving tighter lower bounds and matching upper bounds.
result DP-KLUCB and DP-IMED achieve asymptotically optimal regret under ε-global DP.
New algorithm achieves consistent learning from context in bandit problems.
problem Learning from context in bandit problems with non-i.i.d. contexts.
method Optimistically universal learning rule balancing generalization and personalization.
result Achieves universal consistency for large classes of non-i.i.d. contexts.
Paper proposes an online learning method with multi-level adaptivity for diverse loss functions.
problem Online learning with unknown types and curvatures of functions.
method Multi-layer online ensemble approach with gradient variations.
result Achieves improved regret bounds for different types of loss functions.
New algorithm reduces regret in private online learning with optimal gap-dependent rate.
problem Optimal gap-dependent regret rate for private stochastic decision-theoretic online learning.
method Horizon-free pure-DP algorithm with exponential block partitioning and softmax selection.
result Explicit regret bound of 1000 ⋅ ( log K Δ min + log K ε ) 1000 \cdot (\frac{\log K}{Δ_{\min}}+\frac{\log K}{\varepsilon}) 1000 ⋅ ( Δ m i n l o g K + ε l o g K ) . New algorithm reduces regret in multi-armed bandit problems with Gaussian rewards.
problem Optimizing decisions in multi-armed bandit problems with Gaussian rewards.
method Proposed TSCG and UTSCG algorithms using Thompson Sampling with Gaussian prior.
result Achieved lower regret bounds for optimal arm selection.
New algorithm for online portfolio selection with reduced runtime.
problem Maximizing total return in online portfolio selection.
method Minimizes current logarithmic loss regularized by log-determinant of Hessian.
result Achieves regret guarantee similar to Universal Portfolios with reduced runtime.
New concept of proper-calibeating extends classic calibrated forecasts to proper scoring rules.
problem Defining and extending calibrated forecasts to proper scoring rules.
method Extending the concepts of calibrated and calibeating forecasts to proper scoring rules and proving their properties.
result Proper-calibration always implies calibration, but proper-calibeating does not necessarily imply calibeating.
We consider the classical problem of sequential resource allocation where a decision maker must repeatedly divide a budget between several resources, each with diminishing returns. This can be recast as a specific stochastic optimization problem where the objective is to maximize the cumulative reward, or equivalently …
Algorithm minimizes control regret for non-stationary LQR systems.
problem Control of non-stationary LQR systems with unknown dynamics.
method Adaptive non-stationarity detection and OLS estimator with small bias.
result Achieves optimal dynamic regret of $ ilde{\mathcal{O}}\left(V_T^{2/5}T^{3/5}
ight)$ .
Adaptive speculative decoding framework for LLMs using bandit algorithms.
problem Adaptive speculative decoding for LLMs to balance speed and quality.
method Formulated as a Multi-Armed Bandit problem, proposed UCBSpec and EXP3Spec algorithms.
result UCBSpec algorithm achieves optimal regret performance up to universal constants.
The study analyzes how covariance estimation errors affect the global minimum-variance portfolio under heavy-tailed distributions.
problem The impact of covariance estimation errors on the global minimum-variance portfolio under heavy-tailed distributions.
method Characterization of covariance-estimation error's effect on GMVP suboptimality, derivation of regret identity and bound, application to heavy-tailed returns.
result The decision geometry of GMVP regret is invariant to a (p-1)-dimensional projection of the error matrix, with invariance to the covariance-scale direction as an exact special case.
Transformer pretraining yields strong EB performance without explicit adaptation.
problem Empirical Bayes problems with unknown test distributions.
method Indirect analysis of pretrained transformer's performance under universal priors.
result Near-optimal regret bound of O ~ ( 1 n ) \widetilde{O}(\frac{1}{n}) O ( n 1 ) for arbitrary test distributions. New algorithm handles bandit problems under translations and scales.
problem Adversarial multi-armed bandit problems with arbitrary translations and scales.
method Innovative online algorithm invariant to translations and scales, using universal prediction.
result Second-order regret bounds, unaffected by affine transformations of losses.
HyperBO+ pre-trains a universal prior for Bayesian optimization across different domains.
problem Bayesian optimization requires domain-specific priors, limiting its applicability.
method Two-step pre-training method for hierarchical Gaussian processes.
result HyperBO+ achieves lower regrets on unseen search spaces.
Optimal algorithm for linear bandits on ellipsoids with minimax regret bound.
problem Linear stochastic bandits on ellipsoids.
method Novel sequential procedure to estimate norm of parameters, followed by an explore-and-commit strategy.
result Regret bound matches minimax lower bound with multiplicative constant.