paper-with-me

Papers

AdaSpring: Context-adaptive and Runtime-evolutionary Deep Model Compression for Mobile Applications

2021-01-28 · Sicong Liu, Bin Guo, Ke Ma, Zhiwen Yu, Junzhao Du

There are many deep learning (e.g., DNN) powered mobile and wearable applications today continuously and unobtrusively sensing the ambient surroundings to enhance all aspects of human lives. To enable robust and private mobile sensing, DNN tends to be deployed locally on the resource-constrained mobile devices via model compression. The current practice either hand-crafted DNN compression techniques, i.e., for optimizing DNN-relative performance (e.g., parameter size), or on-demand DNN compression methods, i.e., for optimizing hardware-dependent metrics (e.g., latency), cannot be locally online because they require offline retraining to ensure accuracy. Also, none of them have correlated their efforts with runtime adaptive compression to consider the dynamic nature of the deployment context of mobile applications. To address those challenges, we present AdaSpring, a context-adaptive and self-evolutionary DNN compression framework. It enables the runtime adaptive DNN compression locally online. Specifically, it presents the ensemble training of a retraining-free and self-evolutionary network to integrate multiple alternative DNN compression configurations (i.e., compressed architectures and weights). It then introduces the runtime search strategy to quickly search for the most suitable compression configurations and evolve the corresponding weights. With evaluation on five tasks across three platforms and a real-world case study, experiment outcomes show that AdaSpring obtains up to 3.1x latency reduction, 4.2 x energy efficiency improvement in DNNs, compared to hand-crafted compression techniques, while only incurring <= 6.2ms runtime-evolution latency.

📄 PDF Abstract BibTeX arXiv:2101.11800

Code (0)

등록된 구현이 없습니다.

Tasks

Model Compression

Similar Papers 제목 키워드 기반

From Retrieved Context to Runtime Control: Adaptive Compression for Edge-based RAG

2026-08-20 · Zlatan Feric, Amir Taherin, Yanzhi Wang, David Kaeli arxiv

Retrieval-augmented generation (RAG) improves language-model responses by grounding generation in external passages, which comes with overhead: retrieved context lengthens the prompt, increasing prefill work, KV-cache fo…

Natural Questions

EvolKV: Evolutionary KV Cache Compression for LLM Inference

2025-09-10 · Bohan Yu, Yekun Chai arxiv

Existing key-value (KV) cache compression methods typically rely on heuristics, such as uniform cache allocation across layers or static eviction policies, however, they ignore the critical interplays among layer-specifi…

Code Completion

Runtime-Certified Bounded-Error Quantized Attention

2026-05-20 · Dean Calver arxiv

KV cache quantization reduces the memory cost of long-context LLM inference, but introduces approximation error that is typically validated only empirically. Existing systems rely on average-case robustness, with no mech…

Language Modelling

Fixed-Target Runtime Analysis

2020-04-20 · Maxim Buzdalov, Benjamin Doerr, Carola Doerr, Dmitry Vinokurov

Runtime analysis aims at contributing to our understanding of evolutionary algorithms through mathematical analyses of their runtimes. In the context of discrete optimization problems, runtime analysis classically studie…

Evolutionary Algorithms

When Does Hillclimbing Fail on Monotone Functions: An entropy compression argument

2018-08-03 · Johannes Lengler, Anders Martinsson, Angelika Steger

Hillclimbing is an essential part of any optimization algorithm. An important benchmark for hillclimbing algorithms on pseudo-Boolean functions $f: \{0,1\}^n \to \mathbb{R}$ are (strictly) montone functions, on which a s…