Search Results for author:
Found 15 papers, 2 papers with code
Boosting In-Context Learning in LLMs Through the Lens of Classical Supervised Learning
While calibration techniques are proposed to mitigate these biases, we show that, in the logit space, many of these methods are equivalent to merely shifting the LLM's decision boundary without having the ability to alter its orientation.
Teleportation With Null Space Gradient Projection for Optimization Acceleration
Optimization techniques have become increasingly critical due to the ever-growing model complexity and data scale.
S2TX: Cross-Attention Multi-Scale State-Space Transformer for Time Series Forecasting
Time series forecasting has recently achieved significant progress with multi-scale models to address the heterogeneity between long and short range patterns.
Score-Based Metropolis-Hastings Algorithms
In this paper, we introduce a new approach for integrating score-based models with the Metropolis-Hastings algorithm.
Offline Stochastic Optimization of Black-Box Objective Functions
Many challenges in science and engineering, such as drug discovery and communication network design, involve optimizing complex and expensive black-box functions across vast search spaces.
CATE Estimation With Potential Outcome Imputation From Local Regression
To address this issue, we propose a model-agnostic data augmentation method for CATE estimation.
Robust Reinforcement Learning through Efficient Adversarial Herding
In this work, we extend the two-player game by introducing an adversarial herd, which involves a group of adversaries, in order to address ($\textit{i}$) the difficulty of the inner optimization problem, and ($\textit{ii}$) the potential over pessimism caused by the selection of a candidate adversary set that may include unlikely scenarios.
Mode-Aware Continual Learning for Conditional Generative Adversarial Networks
To this end, we introduce a new continual learning approach for conditional generative adversarial networks by leveraging a mode-affinity score specifically designed for generative modeling.
PASTA: Pessimistic Assortment Optimization
The objective is to use the offline dataset to find an optimal assortment.
Domain Adaptation via Rebalanced Sub-domain Alignment
To address this limitation, we propose a novel generalization bound that reweights source classification error by aligning source and target sub-domains.
Transfer Learning for Individual Treatment Effect Estimation
To this end, we theoretically assess the feasibility of transferring ITE knowledge and present a practical framework for efficient transfer.
Multi-Agent Adversarial Attacks for Multi-Channel Communications
In particular, by modeling the adversaries as learning agents, we show that the proposed MAAS is able to successfully choose the transmitted channel(s) and their respective allocated power(s) without any prior knowledge of the sender strategy.
Blaschke Product Neural Networks (BPNN): A Physics-Infused Neural Network for Phase Retrieval of Meromorphic Functions
To this end, we propose a physics-infused deep neural network based on the Blaschke products for phase retrieval.
Task Affinity with Maximum Bipartite Matching in Few-Shot Learning
We propose an asymmetric affinity score for representing the complexity of utilizing the knowledge of one task for learning another one.
Fisher Task Distance and Its Application in Neural Architecture Search
Next, we construct an online neural architecture search framework using the Fisher task distance, in which we have access to the past learned tasks.
