Zeroth-order optimization with orthogonal random directions
PulseAugur coverage of Zeroth-order optimization with orthogonal random directions — every cluster mentioning Zeroth-order optimization with orthogonal random directions across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
ZOTTA framework uses gradient-free optimization for test-time adaptation
Researchers have developed ZOTTA, a novel test-time adaptation (TTA) framework that utilizes gradient-free zeroth-order optimization (ZOO) to enhance model robustness under distribution shifts. Unlike traditional method…
-
New IPZO architecture enhances SNN fine-tuning on IMC accelerators
Researchers have developed an Event-triggered Implicit Perturbation (IPZO) architecture to improve the efficiency of fine-tuning spiking neural networks (SNNs) on in-memory computing (IMC) accelerators. This new approac…
-
New CAZO method enhances memory-efficient test-time adaptation
Researchers have developed a new zeroth-order optimization method called Curvature-Aware Zeroth-Order Optimization (CAZO) for memory-efficient test-time adaptation (TTA). This method aims to improve the performance of p…
-
QScheduler algorithm enables adaptive on-device AI training on microcontrollers
Researchers have developed QScheduler, an adaptive algorithm designed to optimize on-device training for microcontrollers equipped with Neural Processing Units (NPUs). This method estimates gradients using only forward …
-
New TTA method uses ZOO and model merging for resource-limited devices
Researchers have developed a new method for test-time adaptation (TTA) that addresses the resource limitations of edge devices. By integrating zeroth-order optimization (ZOO) with model merging within a cross-device col…
-
New SHIELD-IDS enhances ML intrusion detection against adversarial attacks
Researchers have developed SHIELD-IDS, an enhanced intrusion detection system designed to combat adversarial attacks on machine learning models. The system integrates gradient boosting models like XGBoost and LightGBM i…
-
New AR1-ZO method boosts LoRA fine-tuning with Zeroth-Order optimization
Researchers have developed AR1-ZO, a novel method for fine-tuning large language models using Zeroth-Order optimization and Low-Rank Adaptation (LoRA). This technique addresses the challenge of effectively increasing Lo…