paper-with-me

홈 › Papers

Adaptive Inference: Theoretical Limits and Unexplored Opportunities

2024-02-06 · Soheil Hor, Ying Qian, Mert Pilanci, Amin Arbabian

This paper introduces the first theoretical framework for quantifying the efficiency and performance gain opportunity size of adaptive inference algorithms. We provide new approximate and exact bounds for the achievable efficiency and performance gains, supported by empirical evidence demonstrating the potential for 10-100x efficiency improvements in both Computer Vision and Natural Language Processing tasks without incurring any performance penalties. Additionally, we offer insights on improving achievable efficiency gains through the optimal selection and design of adaptive inference state spaces.

📄 PDF Abstract BibTeX arXiv:2402.04359

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On Theoretical Limits of Learning with Label Differential Privacy

2025-02-20 · Puning Zhao, Chuan Ma, Li Shen, Shaowei Wang 외

Label differential privacy (DP) is designed for learning problems involving private labels and public features. While various methods have been proposed for learning under label DP, the theoretical limits remain largely …

A2D2: Fine-Tuning Any-Length Discrete Diffusion for Adaptive Decoding

2026-06-11 · Sophia Tang, Yuchen Zhu, Molei Tao, Pranam Chatterjee arxiv

Discrete diffusion models offer a simple and stable likelihood-based framework for sequence generation, recently extended to any-length settings via token insertion. Principled reward-guided fine-tuning for any-length di…

The Edge Density Barrier: Computational-Statistical Tradeoffs in Combinatorial Inference

2018-07-01 · ICML 2018 7 · Hao Lu, Yuan Cao, Zhuoran Yang, Junwei Lu 외

We study the hypothesis testing problem of inferring the existence of combinatorial structures in undirected graphical models. Although there exist extensive studies on the information-theoretic limits of this probl…

Two-sample testing

Understanding Predictive Coding as an Adaptive Trust-Region Method

2023-05-29 · Francesco Innocenti, Ryan Singh, Christopher L. Buckley

Predictive coding (PC) is a brain-inspired local learning algorithm that has recently been suggested to provide advantages over backpropagation (BP) in biologically relevant scenarios. While theoretical work has mainly f…

Slim-SC: Thought Pruning for Efficient Scaling with Self-Consistency

2025-09-17 · Colin Hong, Xu Guo, Anand Chaanan Singh, Esha Choukse 외 arxiv

Recently, Test-Time Scaling (TTS) has gained increasing attention for improving LLM reasoning performance at test time without retraining the model. A notable TTS technique is Self-Consistency (SC), which generates multi…