Hierarchical Proxy Modeling for Improved HPO in Time Series Forecasting

Jati, Arindam; Ekambaram, Vijay; Shaonli, Pal,; Quanz, Brian; Gifford, Wesley M.; Harsha, Pavithra; Siegel, Stuart E.; Mukherjee, Saurabh; Narayanaswami, Chandra

doi:10.1145/3580305.3599378

Cited by 2 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For SO and Application data, we used the number of Mixer layers (nl)= 8 and dropout (do) = 0.4, and for the Service and L2C data, nl = 3 and do = 0.3. The training, validation, and test sets are chronologically split in a ratio of 0.6 : 0.2 : 0.2 using temporal cross-validation (Jati et al 2023). For all training, we incorporated early stopping based on the validation performance.…”

Section: Experimental Settingmentioning

confidence: 99%

AutoMixer for Improved Multivariate Time-Series Forecasting on Business and IT Observability Data

Palaskar,

Ekambaram,

Jati

et al. 2024

AAAI

View full text Add to dashboard Cite

The efficiency of business processes relies on business key performance indicators (Biz-KPIs), that can be negatively impacted by IT failures. Business and IT Observability (BizITObs) data fuses both Biz-KPIs and IT event channels together as multivariate time series data. Forecasting Biz-KPIs in advance can enhance efficiency and revenue through proactive corrective measures. However, BizITObs data generally exhibit both useful and noisy inter-channel interactions between Biz-KPIs and IT events that need to be effectively decoupled. This leads to suboptimal forecasting performance when existing multivariate forecasting models are employed. To address this, we introduce AutoMixer, a time-series Foundation Model (FM) approach, grounded on the novel technique of channel-compressed pretrain and finetune workflows. AutoMixer leverages an AutoEncoder for channel-compressed pretraining and integrates it with the advanced TSMixer model for multivariate time series forecasting. This fusion greatly enhances the potency of TSMixer for accurate forecasts and also generalizes well across several downstream tasks. Through detailed experiments and dashboard analytics, we show AutoMixer's capability to consistently improve the Biz-KPI's forecasting accuracy (by 11-15%) which directly translates to actionable business insights.

show abstract

Section: Experimental Settingmentioning

confidence: 99%