Asia
The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization
Constantinos Daskalakis, Ioannis Panageas
We characterize the limit points of two basic first order methods, namely Gradient Descent/Ascent (GDA) and Optimistic Gradient Descent Ascent (OGDA).
On Markov Chain Gradient Descent
Tao Sun, Yuejiao Sun, Wotao Yin
Neural Information Processing Systems http://nips.cc/
Stochastic Nested Variance Reduced Gradient Descent for Nonconvex Optimization
Dongruo Zhou, Pan Xu, Quanquan Gu
Neural Information Processing Systems http://nips.cc/
Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks Andy Zhou
Despite advances in AI alignment, large language models (LLMs) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries can modify prompts to induce unwanted behavior.
BridgingtheGapbetweenObjectandImage-level RepresentationsforOpen-VocabularyDetection
Open-vocabulary detection (OVD) aims to generalize beyond the limited number of base classes labeled during the training phase. The goal is to detect novel classes defined by an unbounded (open)vocabularyatinference.
Semi-Supervised Learning with Declaratively Specified Entropy Constraints
Haitian Sun, William W. Cohen, Lidong Bing
Neural Information Processing Systems http://nips.cc/
Submodular Function Minimization with Noisy Evaluation Oracle
Neural Information Processing Systems http://nips.cc/
Data-Driven Clustering via Parameterized Lloyd's Families
Maria-Florina F. Balcan, Travis Dick, Colin White
Neural Information Processing Systems http://nips.cc/