平滑校准，泄漏预测，有限召回和纳什动态
Smooth Calibration, Leaky Forecasts, Finite Recall, and Nash Dynamics
摘要：
我们建议通过结合附近的预测来平滑校准分数，该分数衡量预报员的好坏。虽然定期校准可以保证只有通过随机预测程序，我们表明，平滑校准可以保证确定性的程序。因此，预测是否泄露并不重要，即，提前告知：仍然可以保证顺利校准（而定期校准则不能）。此外，我们的程序具有有限的召回，是固定的，所有的预测都位于一个有限的网格。为了构建该程序，我们还处理了在线线性回归和弱校准的相关设置。最后，我们证明了平滑校准在n人游戏中产生非耦合的有限记忆动态“平滑校准学习”，其中玩家在几乎所有时期都玩近似的纳什均衡（相比之下，使用规则的校准学习）校准，只产生游戏的时间平均值是近似相关均衡）。
英文摘要：
We propose to smooth out the calibration score, which measures how good a forecaster is, by combining nearby forecasts. While regular calibration can be guaranteed only by randomized forecasting procedures, we show that smooth calibration can be guaranteed by deterministic procedures. As a consequence, it does not matter if the forecasts are leaked, i.e., made known in advance: smooth calibration can nevertheless be guaranteed (while regular calibration cannot). Moreover, our procedure has finite recall, is stationary, and all forecasts lie on a finite grid. To construct the procedure, we deal also with the related setups of online linear regression and weak calibration. Finally, we show that smooth calibration yields uncoupled finite-memory dynamics in n-person games "smooth calibrated learning" in which the players play approximate Nash equilibria in almost all periods (by contrast, calibrated learning, which uses regular calibration, yields only that the time-averages of play are approximate correlated equilibria).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
