Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding

This work aims at decreasing the end-to-end generation latency of large language models (LLMs). One of the major causes of the high generation latency is the sequential decoding approach adopted by almost all state-of-the-art LLMs. In this work, motivated by the thinking and writing process of humans, we propose "Skeleton-of-Thought" (SoT), which guides LLMs to first generate the skeleton of the answer, and then conducts parallel API calls or batched decoding to complete the contents of each skeleton point in parallel. Not only does SoT provide considerable speed-up (up to 2.39x across 11 different LLMs), but it can also potentially improve the answer quality on several question categories in terms of diversity and relevance. SoT is an initial attempt at data-centric optimization for efficiency, and reveal the potential of pushing LLMs to think more like a human for answer quality.

Dynamic Ensemble of Low-fidelity Experts: Mitigating NAS "Cold-Start"

Predictor-based Neural Architecture Search (NAS) employs an architecture performance predictor to improve the sample efficiency. However, predictor-based NAS suffers from the severe ``cold-start'' problem, since a large amount of architecture-performance data is required to get a working predictor. In this paper, we focus on exploiting information in cheaper-to-obtain performance estimations (i.e., low-fidelity information) to mitigate the large data requirements of predictor training. Despite the intuitiveness of this idea, we observe that using inappropriate low-fidelity information even damages the prediction ability and different search spaces have different preferences for low-fidelity information types. To solve the problem and better fuse beneficial information provided by different types of low-fidelity information, we propose a novel dynamic ensemble predictor framework that comprises two steps. In the first step, we train different sub-predictors on different types of available low-fidelity information to extract beneficial knowledge as low-fidelity experts. In the second step, we learn a gating network to dynamically output a set of weighting coefficients conditioned on each input neural architecture, which will be used to combine the predictions of different low-fidelity experts in a weighted sum. The overall predictor is optimized on a small set of actual architecture-performance data to fuse the knowledge from different low-fidelity experts to make the final prediction. We conduct extensive experiments across five search spaces with different architecture encoders under various experimental settings. Our method can easily be incorporated into existing predictor-based NAS frameworks to discover better architectures.

CLOSE: Curriculum Learning On the Sharing Extent Towards Better One-shot NAS

One-shot Neural Architecture Search (NAS) has been widely used to discover architectures due to its efficiency. However, previous studies reveal that one-shot performance estimations of architectures might not be well correlated with their performances in stand-alone training because of the excessive sharing of operation parameters (i.e., large sharing extent) between architectures. Thus, recent methods construct even more over-parameterized supernets to reduce the sharing extent. But these improved methods introduce a large number of extra parameters and thus cause an undesirable trade-off between the training costs and the ranking quality. To alleviate the above issues, we propose to apply Curriculum Learning On Sharing Extent (CLOSE) to train the supernet both efficiently and effectively. Specifically, we train the supernet with a large sharing extent (an easier curriculum) at the beginning and gradually decrease the sharing extent of the supernet (a harder curriculum). To support this training strategy, we design a novel supernet (CLOSENet) that decouples the parameters from operations to realize a flexible sharing scheme and adjustable sharing extent. Extensive experiments demonstrate that CLOSE can obtain a better ranking quality across different computational budget constraints than other one-shot supernets, and is able to discover superior architectures when combined with various search strategies. Code is available at https://github.com/walkerning/aw_nas.

A Surgery of the Neural Architecture Evaluators

Neural architecture search (NAS) recently received extensive attention due to its effectiveness in automatically designing effective neural architectures. A major challenge in NAS is to conduct a fast and accurate evaluation of neural architectures. Commonly used fast architecture evaluators include one-shot evaluators (including weight sharing and hypernet-based ones) and predictor-based evaluators. Despite their high evaluation efficiency, the evaluation correlation of these evaluators is still questionable. In this paper, we conduct an extensive assessment of both the one-shot and predictor-based evaluator on the NAS-Bench-201 benchmark search space, and break up how and why different factors influence the evaluation correlation and other NAS-oriented criteria. Codes are available at https://github.com/walkerning/aw_nas.

Recurrent and Spiking Modeling of Sparse Surgical Kinematics

Robot-assisted minimally invasive surgery is improving surgeon performance and patient outcomes. This innovation is also turning what has been a subjective practice into motion sequences that can be precisely measured. A growing number of studies have used machine learning to analyze video and kinematic data captured from surgical robots. In these studies, models are typically trained on benchmark datasets for representative surgical tasks to assess surgeon skill levels. While they have shown that novices and experts can be accurately classified, it is not clear whether machine learning can separate highly proficient surgeons from one another, especially without video data. In this study, we explore the possibility of using only kinematic data to predict surgeons of similar skill levels. We focus on a new dataset created from surgical exercises on a simulation device for skill training. A simple, efficient encoding scheme was devised to encode kinematic sequences so that they were amenable to edge learning. We report that it is possible to identify surgical fellows receiving near perfect scores in the simulation exercises based on their motion characteristics alone. Further, our model could be converted to a spiking neural network to train and infer on the Nengo simulation framework with no loss in accuracy. Overall, this study suggests that building neuromorphic models from sparse motion features may be a potentially useful strategy for identifying surgeons and gestures with chips deployed on robotic systems to offer adaptive assistance during surgery and training with additional latency and privacy benefits.