Time series forecasting is one of the most essential and ubiquitous tasks in many business problems, including demand forecasting and logistics optimization. Traditional time series forecasting methods, however, have resulted in small models with limited expressive power because they have difficulty in scaling their model size up while maintaining high accuracy. In this paper, we propose Forecasting orchestra (Forchestra), a simple but powerful framework capable of accurately predicting future demand for a diverse range of items. We empirically demonstrate that the model size is scalable to up to 0.8 billion parameters. The proposed method not only outperforms existing forecasting models with a significant margin, but it could generalize well to unseen data points when evaluated in a zero-shot fashion on downstream datasets. Last but not least, we present extensive qualitative and quantitative studies to analyze how the proposed model outperforms baseline models and differs from conventional approaches. The original paper was presented as a full paper at ICDM 2022 and is available at: https://ieeexplore.ieee.org/document/10027662.

This paper presents a plug-and-play approach for translation with terminology constraints. Terminology constraints are an important aspect of many modern translation pipelines. In both specialized domains and newly emerging domains (such as the COVID-19 pandemic), accurate translation of technical terms is crucial. Recent approaches often train models to copy terminologies from the input into the output sentence by feeding the target terminology along with the input. But this requires expensive training whenever the underlying language model is changed or the system should specialize to a new domain. We propose Cascade Beam Search, a plug-and-play terminology-forcing approach that requires no training. Cascade Beam Search has two parts: 1) logit manipulation to increase the probability of target terminologies and 2) a cascading beam setup based on grid beam search, where beams are grouped by the number of terminologies they contain. We evaluate the performance of our approach by competing against the top submissions of the WMT21 terminology translation task. Our plug-and-play approach performs on par with the winning submissions without using a domain-specific language model and with no additional training.

Analog in-memory computing-a promising approach for energy-efficient acceleration of deep learning workloads-computes matrix-vector multiplications but only approximately, due to nonidealities that often are non-deterministic or nonlinear. This can adversely impact the achievable inference accuracy. Here, we develop an hardware-aware retraining approach to systematically examine the accuracy of analog in-memory computing across multiple network topologies, and investigate sensitivity and robustness to a broad set of nonidealities. By introducing a realistic crossbar model, we improve significantly on earlier retraining approaches. We show that many larger-scale deep neural networks-including convnets, recurrent networks, and transformers-can in fact be successfully retrained to show iso-accuracy with the floating point implementation. Our results further suggest that nonidealities that add noise to the inputs or outputs, not the weights, have the largest impact on accuracy, and that recurrent networks are particularly robust to all nonidealities.

Demand forecasting is a crucial component of supply chain management for revenue optimization and inventory planning. Traditional time series forecasting methods, however, have resulted in small models with limited expressive power because they have difficulty in scaling their model size up while maintaining high accuracy. In this paper, we propose Forecasting orchestra (Forchestra), a simple but powerful ensemble framework capable of accurately predicting future demand for a diverse range of items. Forchestra consists of two parts: 1) base predictors and 2) a neural conductor. For a given time series, each base predictor outputs its respective forecast based on historical observations. On top of the base predictors, the neural conductor adaptively assigns the importance weight for each predictor by looking at the representation vector provided by a representation module. Finally, Forchestra aggregates the predictions by the weights and constructs a final prediction. In contrast to previous ensemble approaches, the neural conductor and all base predictors of Forchestra are trained in an end-to-end manner; this allows each base predictor to modify its reaction to different inputs, while supporting other predictors and constructing a final prediction jointly. We empirically show that the model size is scalable to up to 0.8 billion parameters ($\approx$400-layer LSTM). The proposed method is evaluated on our proprietary E-Commerce (100K) and the public M5(30K) datasets, and it outperforms existing forecasting models with a significant margin. In addition, we observe that our framework generalizes well to unseen data points when evaluated in a zeroshot fashion on downstream datasets. Last but not least, we present extensive qualitative and quantitative studies to analyze how the proposed model outperforms baseline models and differs from conventional ensemble approaches. The code is available at https://github.com/young-j-parld22-ICDM-Forchestra.

The precise programming of crossbar arrays of unit-cells is crucial for obtaining high matrix-vector-multiplication (MVM) accuracy in analog in-memory computing (AIMC) cores. We propose a radically different approach based on directly minimizing the MVM error using gradient descent with synthetic random input data. Our method significantly reduces the MVM error compared with conventional unit-cell by unit-cell iterative programming. It also eliminates the need for high-resolution analog-to-digital converters (ADCs) to read the small unit-cell conductance during programming. Our method improves the experimental inference accuracy of ResNet-9 implemented on two phase-change memory (PCM)-based AIMC cores by 1.26%.