We introduce Annealed Multiple Choice Learning (aMCL) which combines simulated annealing with MCL. MCL is a learning framework handling ambiguous tasks by predicting a small set of plausible hypotheses. These hypotheses are trained using the Winner-takes-all (WTA) scheme, which promotes the diversity of the predictions. However, this scheme may converge toward an arbitrarily suboptimal local minimum, due to the greedy nature of WTA. We overcome this limitation using annealing, which enhances the exploration of the hypothesis space during training. We leverage insights from statistical physics and information theory to provide a detailed description of the model training trajectory. Additionally, we validate our algorithm by extensive experiments on synthetic datasets, on the standard UCI benchmark, and on speech separation.

翻译：本文提出退火多选学习（aMCL）方法，将模拟退火与多选学习（MCL）相结合。MCL是一种通过预测少量合理假设来处理模糊任务的学习框架，其假设训练采用赢家通吃（WTA）机制以提升预测多样性。然而，由于WTA的贪婪特性，该机制可能收敛至任意次优局部极小值。我们通过引入退火机制克服此局限，在训练过程中增强假设空间的探索能力。借助统计物理学与信息论的洞见，我们对模型训练轨迹进行了精细化描述。此外，我们在合成数据集、标准UCI基准测试及语音分离任务上通过大量实验验证了算法的有效性。