AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

Discrete Continuous Optimization Framework for Simultaneous Clustering and Training in Mixture Models

Parth Vipul Sangani, Arjun Shashank Kashettiwar, Pritish Chakraborty, Bhuvan Reddy Gangula, Durga S, Ganesh Ramakrishnan, Rishabh K Iyer, Abir De

ICML 2023 · Learning theory and algorithms › Clustering · approach: Clustering approximation algorithms

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Joint discrete-continuous partitioning and training (PRESTO) instead of MoE / unsupervised partitioningmixture of ResNet18-reduced components · CIFAR10Accuracy: 95.49 vs 90.02 (MoE, second best)Improved
Joint discrete-continuous partitioning and training (PRESTO) instead of baselinesmixture of ResNet18-reduced components · CIFAR100Accuracy: 94.86 vs 85.19 (MoE, second best)Improved
Joint discrete-continuous partitioning and training (PRESTO) instead of baselinesmixture of ResNet18-reduced components · STLAccuracy: 90.07 vs 81.93 (Learn-MLR, second best)Improved
Joint partitioning/training (PRESTO) vs knowledge distillation and pruning in resource-constrained settingPRESTO lightweight partitioned models · CIFAR10GPU memory during training (MiB): 58.12 vs 274.27 (KD)Improved
Partitioned lightweight models (PRESTO) vs KD at inferencePRESTO lightweight partitioned models · CIFAR10GPU memory at test (MiB): 12.07 vs 27.61 (KD)Improved
Increasing number of partitions K from 4 to 7 (ablation)PRESTO · CIFAR10, CIFAR100, STLAccuracyMixed
Accuracy-vs-K sweep for PRESTO (partition count) (ablation)PRESTO · CIFAR10AccuracyMixed
Joint partitioning and training (PRESTO) vs Agglomerative clustering on synthetic dataPRESTO · Synthetic degenerate mixtureARI: 0.92 vs 0.79 (Agglomerative)Improved
Joint partitioning and training (PRESTO) vs Kmeans++ / Learn-MLR for partition quality on CIFAR10/CIFAR100PRESTO · CIFAR100ICD (inter-cluster dissimilarity): PRESTO 0.712 vs MoE 0.743Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy