The leaders of eight German states have backed the nation's chancellor amid growing speculation about his political future. The premiers - all of whom are part of Friedrich Merz's Christian Democratic Union (CDU) - wrote that restoring trust in their party lay in listening and taking political action, not in debates over personnel. Merz, who has only held the post for 16 months, is facing poor approval ratings while the anti-immigration, far-right Alternative for Germany (AfD) party is surging, prompting questions about whether he is an electoral liability. He has vowed to carry on but two more state elections on Sunday have been seen as a key test of his leadership. Rumours of a Kanzlertausch - or Chancellor swap - have been around for months, but they have increased since the conservative CDU tumbled to a distant second behind the AfD in the eastern state of Saxony-Anhalt at the start of September. The AfD shot up to 43.8% of the vote while the CDU plummeted to 17.2%, marking the first time since World War Two that a far-right party has come close to controlling a German state.

Follow this section to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Follow this tag to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW?

Follow this section to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Follow this tag to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW?

We developed task-optimized deep neural networks (DNNs) that achieved state-ofthe-art performance in different evaluation scenarios for automatic music tagging. These DNNs were subsequently used to probe the neural representations of music. Representational similarity analysis revealed the existence of a representational gradient across the superior temporal gyrus (STG). Anterior STG was shown to be more sensitive to low-level stimulus features encoded in shallow DNN layers whereas posterior STG was shown to be more sensitive to high-level stimulus features encoded in deep DNN layers.

We study bandit best-arm identification with arbitrary and potentially adversarial rewards. A simple random uniform learner obtains the optimal rate of error in the adversarial scenario. However, this type of strategy is suboptimal when the rewards are sampled stochastically. Therefore, we ask: Can we design a learner that performs optimally in both the stochastic and adversarial problems while not being aware of the nature of the rewards? First, we show that designing such a learner is impossible in general. In particular, to be robust to adversarial rewards, we can only guarantee optimal rates of error on a subset of the stochastic problems. We give a lower bound that characterizes the optimal rate in stochastic problems if the strategy is constrained to be robust to adversarial rewards. Finally, we design a simple parameter-free algorithm and show that its probability of error matches (up to log factors) the lower bound in stochastic problems, and it is also robust to adversarial ones.

PsHD compared to sample representation and pair-wise similarity distillation methods theoretically and experimentally.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/