This paper introduces TabPack, an efficient MLP ensemble for tabular data that samples and trains MLPs with different hyperparameters in parallel and selects ensemble members on-the-fly during trainin…

This paper proposes a game-theoretic framework using Shapley Effects and Pareto front sets for interpretable hyperparameter-objective interaction analysis.

This paper investigates the application of Parameter-Efficient Fine-Tuning (PEFT) methods, specifically adapters and LoRA, to large pretrained models for instance segmentation, demonstrating that thes…

TRACE proposes a novel method to mitigate catastrophic forgetting in continual LLM fine-tuning by identifying and isolating a small, task-specific subset of essential parameters for each task.

The paper reframes Parameter-Efficient Fine-Tuning (PEFT) from a mere cost-saving alternative to a robust architecture for creating persistent, personalized models that layer specific behaviors onto l…

The paper proposes a novel exponential mechanism using quadratic approximations to fine-tune machine learning models on sensitive data while providing strong differential privacy guarantees.

This paper introduces a method to automatically determine the optimal learning period ($ au$) for the Random Gradient hyper-heuristic, enabling it to optimally solve Pseudo-Boolean Problems without ma…

This paper rigorously proves that a Reinforcement Learning Hyper-heuristic (RLHH) optimizes the LeadingOnes benchmark function with optimal expected runtime using two random local search operators, ou…

The authors compare and evaluate 20 software configuration optimizers based on six assumptions about the data, and find that no single optimizer outperforms others across all budgets. They propose a t…

The paper proposes Self-Adaptive Monotonic Normalization (SAMN), a hyperparameter-friendly method that improves long-tailed recognition by enforcing monotonicity on per-class weight norms without requ…

The paper presents a framework for model selection and parameter estimation using large language models and neural simulation-based inference.

ParaTool introduces a novel framework that shifts tool representations from bulky context documentation to dedicated, loadable parameters, enabling efficient and robust tool calling in LLMs.

A new method for selecting knots in Generalized Additive Models using an extension of adaptive splines and a customized Fellner-Schall scheme.

This paper introduces BBOmix, an open-source benchmark for unsupervised representation learning on real-world biological data.

The paper theoretically analyzes the limitations of parameter-based knowledge editing and empirically demonstrates that these methods consistently damage core LLM capabilities compared to retrieval-ba…

The paper investigates whether using fine-grained, tensorized adapters (CP components) instead of standard LoRA ranks improves the accuracy-budget trade-off in PEFT, finding that while they fill budge…

This paper provides theoretical analysis of parameter settings for the bat algorithm using dynamical systems and population variance theory, and validates the results through numerical experiments.

The paper introduces Safety Bottleneck Regularization (SBR), a novel defense mechanism that anchors LLM safety by constraining the unembedding layer, effectively preventing harmful fine-tuning (HFT) e…

CSULoRA is a post-hoc method that corrects trained LoRA adapters by estimating a safety-aligned subspace and solving a penalized minimum-change problem to attenuate unsafe update directions while pres…