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

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

Rainbow Deep Q-Network (DQN) demonstrated combining multiple independent enhancements could significantly boost a reinforcement learning (RL) agent's performance. In this paper, we present "Beyond The Rainbow" (BTR), a novel algorithm that integrates six improvements from across the RL literature to Rainbow DQN, establishing a new state-of-the-art for RL using a desktop PC, with a human-normalized interquartile mean (IQM) of 7.4 on atari-60. Beyond Atari, we demonstrate BTR's capability to handle complex 3D games, successfully training agents to play Super Mario Galaxy, Mario Kart, and Mortal Kombat with minimal algorithmic changes. Designing BTR with computational efficiency in mind, agents can be trained using a desktop PC on 200 million Atari frames within 12 hours. Additionally, we conduct detailed ablation studies of each component, analzying the performance and impact using numerous measures.

Retrieval augmentation addresses many critical problems in large language models such as hallucination, staleness, and privacy leaks. However, running retrieval-augmented language models (LMs) is slow and difficult to scale due to processing large amounts of retrieved text. We introduce binary token representations (BTR), which use 1-bit vectors to precompute every token in passages, significantly reducing computation during inference. Despite the potential loss of accuracy, our new calibration techniques and training objectives restore performance. Combined with offline and runtime compression, this only requires 127GB of disk space for encoding 3 billion tokens in Wikipedia. Our experiments show that on five knowledge-intensive NLP tasks, BTR accelerates state-of-the-art inference by up to 4x and reduces storage by over 100x while maintaining over 95% task performance.

Pre-trained seq2seq models have achieved state-of-the-art results in the grammatical error correction task. However, these models still suffer from a prediction bias due to their unidirectional decoding. Thus, we propose a bidirectional Transformer reranker (BTR), that re-estimates the probability of each candidate sentence generated by the pre-trained seq2seq model. The BTR preserves the seq2seq-style Transformer architecture but utilizes a BERT-style self-attention mechanism in the decoder to compute the probability of each target token by using masked language modeling to capture bidirectional representations from the target context. For guiding the reranking, the BTR adopts negative sampling in the objective function to minimize the unlikelihood. During inference, the BTR gives final results after comparing the reranked top-1 results with the original ones by an acceptance threshold. Experimental results show that, in reranking candidates from a pre-trained seq2seq model, T5-base, the BTR on top of T5-base could yield 65.47 and 71.27 F0.5 scores on the CoNLL-14 and BEA test sets, respectively, and yield 59.52 GLEU score on the JFLEG corpus, with improvements of 0.36, 0.76 and 0.48 points compared with the original T5-base. Furthermore, when reranking candidates from T5-large, the BTR on top of T5-base improved the original T5-large by 0.26 points on the BEA test set.

We introduce the Sublevel Set (SS) method, a generic method to obtain sufficient guarantees of near-optimality and uniqueness (up to small perturbations) for a clustering. This method can be instantiated for a variety of clustering loss functions for which convex relaxations exist. Obtaining the guarantees in practice amounts to solving a convex optimization. We demonstrate the applicability of this method by obtaining distribution free guarantees for K-means clustering on realistic data sets.

We introduce the Sublevel Set (SS) method, a generic method to obtain sufficient guarantees of near-optimality and uniqueness (up to small perturbations) for a clustering. This method can be instantiated for a variety of clustering loss functions for which convex relaxations exist. Obtaining the guarantees in practice amounts to solving a convex optimization. We demonstrate the applicability of this method by obtaining distribution free guarantees for K-means clustering on realistic data sets.

In designing an exchange mechanism, it is important to Exchange markets (aka double auctions) are the most important achieve a number of desirable properties, namely: maximizing institutions for modern economy, which are centralized social welfare (i.e., efficient), preventing manipulations markets consisting of exchange rules for traders to buy and of agents (i.e., truthful), an agent never pays more sell commodities, e.g. stock exchanges. Most existing studies than what she gets (i.e., individually rational) and the market of exchanges are for the environments where a trader maker should not run the mechanism with a deficit (i.e., is either a buyer or a seller, but not both, of certain commodities budget balanced). It is well known that designing an exchange (Myerson and Satterthwaite 1983; McAfee 1992; mechanism that is efficient, truthful, individually rational Wurman, Walsh, and Wellman 1998; Blum, Sandholm, and and budget balanced is impossible (Myerson and Satterthwaite Zinkevich 2006; Bredin, Parkes, and Duong 2007; Parsons, 1983). Since a loss-making mechanism does not Rodriguez-Aguilar, and Klein 2011).