Follow-the-Leader (FTL) is an intuitive sequential prediction strategy that guarantees constant regret in the stochastic setting, but has terrible performance for worst-case data. Other hedging strategies have better worst-case guarantees but may perform much worse than FTL if the data are not maximally adversarial. We…
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.
169,051 papers · 148 categories
Trend · papers per month
18 results for “Follow-the-Leader”
New algorithms accelerate imitation learning from expert data.
problem Sample inefficiency in reinforcement learning.
method Model-based algorithms inspired by Follow-the-Leader (FTL) with prediction.
result Provable acceleration of convergence rate up to an order.
Most traditional online learning algorithms are based on variants of mirror descent or follow-the-leader. In this paper, we present an online algorithm based on a completely different approach, tailored for transductive settings, which combines "random playout" and randomized rounding of loss subgradients. As an applic…
Paper tackles continual reinforcement learning by forgetting, proposing a planning method with online world models.
problem Catastrophic forgetting in reinforcement learning when learning new tasks.
method Planning with an online world model using model predictive control.
result The proposed FTL Online Agent (OA) learns new tasks without forgetting old skills.
Ensemble of MFESNs improves macroeconomic forecasting.
problem Improving accuracy in macroeconomic forecasting.
method Hedge and Follow-the-Leader schemes applied to MFESNs.
result Ensemble models outperform individual models in forecasting.
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.
This paper proposes a new portfolio allocation method using LLMs to outperform traditional strategies.
problem Persistent tradeoff between risk and return in portfolio management.
method Follow-the-leader approach with sentiment-based trade filtering and LLM-driven hedging.
result Empirical results show a 69% increase in annualized returns and 119% in Sharpe ratio compared to SPY buy-and-hold.
Enhanced trend-following strategy using network momentum for commodity futures.
problem Improving systematic trend-following in commodity futures markets.
method Combines univariate and cross-sectional trend indicators, including network momentum.
result Statistically significant improvements in portfolio performance metrics.
Paper tackles online adaptation to changing label distributions.
problem Adapting machine learning models to changing label distributions in real-world settings.
method Leverages novel analysis to show estimation of expected test loss is possible without true labels. Proposes adaptation algorithms inspired by classical online learning techniques.
result Empirically verified that OGD is particularly effective and robust to various label shift scenarios.
We study the problem of online learning in a class of Markov decision processes known as linearly solvable MDPs. In the stationary version of this problem, a learner interacts with its environment by directly controlling the state transitions, attempting to balance a fixed state-dependent cost and a certain smooth cost…
We present online prediction methods for time series that let us explicitly handle nonstationary artifacts (e.g. trend and seasonality) present in most real time series. Specifically, we show that applying appropriate transformations to such time series before prediction can lead to improved theoretical and empirical p…
We consider the online version of the isotonic regression problem. Given a set of linearly ordered points (e.g., on the real line), the learner must predict labels sequentially at adversarially chosen positions and is evaluated by her total squared loss compared against the best isotonic (non-decreasing) function in hi…
Meta-learning improves performance across similar tasks in adversarial bandit settings.
problem Improving performance across multiple similar tasks in adversarial bandit scenarios.
method Designing meta-algorithms that combine outer learners to tune hyperparameters of inner learners for MAB and BLO.
result Meta-algorithms improve task-averaged regret for MAB and BLO, showing direct relationship with action space-dependent measures.
Unified meta-algorithm improves average performance across similar tasks in adversarial bandits.
problem Improving performance across multiple similar tasks in adversarial bandit settings.
method Unified meta-algorithm for multi-armed bandits and bandit linear optimization, tuning initialization, step-size, and entropy parameters.
result Unified meta-algorithm yields setting-specific guarantees for MAB and BLO, improving task-averaged regret.
Proposes a new training algorithm for zero-sum games to avoid convergence issues.
problem Gradient-based training leads to weak convergence and cyclic dynamics in zero-sum architectures.
method Follow the perturbed leader algorithm with neural mediating agent.
result Guarantees convergence to mixed Nash equilibrium without cyclic behaviors.
Online clustering algorithm with regret bound.
problem Online -means clustering with squared distance objective.
method Multiplicative Weights Update Algorithm (MWUA) with discretized grid and online-to-offline reduction.
result Achieves a regret bound of in expectation.
New algorithm calibrates forecasts in high dimensions with minimal regret.
problem Online calibration of multi-dimensional forecasts over convex sets.
method Connects to external regret minimization for online linear optimization, using swap regret minimization.
result Obtains ε-calibrated forecasts with minimal rounds and without expert knowledge.
Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Setscs.LG
New algorithm exploits curvature of feasible sets for fast online convex optimization.
problem Online convex optimization with fast rates.
method Adapting FTL algorithm to curvature of feasible sets.
result Achieves logarithmic regret bound of in stochastic environments.