Neural Information Processing Systems http://nips.cc/

Right: measurement overthefirst60epochs. Update step adaptation (see Section 4.3)isapplied.

In safety-critical applications, guaranteeing the satisfaction of constraints over continuous environments is crucial, e.g., an autonomous agent should never crash into obstacles or go off-road. Neural models struggle in the presence of these constraints, especially when they involve intricate algebraic relationships. To address this, we introduce a differentiable probabilistic layer that guarantees the satisfaction of non-convex algebraic constraints over continuous variables. This probabilistic algebraic layer (PAL) can be seamlessly plugged into any neural architecture and trained via maximum likelihood without requiring approximations. PAL defines a distribution over conjunctions and disjunctions of linear inequalities, parameterized by polynomials. This formulation enables efficient and exact renormalization via symbolic integration, which can be amortized across different data points and easily parallelized on a GPU. We showcase PAL and our integration scheme on a number of benchmarks for algebraic constraint integration and on real-world trajectory data.

On a long-haul flight, there's nothing worse than being sat next to a chatty stranger. But songbirds don't seem to mind, as a new study suggests they are likely to'talk' to other species as they migrate. Last year, a team of scientists discovered that birds seem to'buddy up' with other species at stopover sites during migration, but there was no evidence that different species pair up or communicate vocally on the wing. But now it's been found that the birds may even chat to gather important information about the journey they are on. For their new study the researchers, from the University of Illinois, analysed more than 18,000 hours of recorded flight calls made over three years in eastern North America.

Constructing datasets representative of the target domain is essential for training effective machine learning models. Active learning (AL) is a promising method that iteratively extends training data to enhance model performance while minimizing data acquisition costs. However, current AL workflows often require human intervention and lack parallelism, leading to inefficiencies and underutilization of modern computational resources. In this work, we introduce PAL, an automated, modular, and parallel active learning library that integrates AL tasks and manages their execution and communication on shared- and distributed-memory systems using the Message Passing Interface (MPI). PAL provides users with the flexibility to design and customize all components of their active learning scenarios, including machine learning models with uncertainty estimation, oracles for ground truth labeling, and strategies for exploring the target space. We demonstrate that PAL significantly reduces computational overhead and improves scalability, achieving substantial speed-ups through asynchronous parallelization on CPU and GPU hardware. Applications of PAL to several real-world scenarios - including ground-state reactions in biomolecular systems, excited-state dynamics of molecules, simulations of inorganic clusters, and thermo-fluid dynamics - illustrate its effectiveness in accelerating the development of machine learning models. Our results show that PAL enables efficient utilization of high-performance computing resources in active learning workflows, fostering advancements in scientific research and engineering applications.

Investigating the genetic architecture of complex diseases is challenging due to the highly polygenic and interactive landscape of genetic and environmental factors. Although genome-wide association studies (GWAS) have identified thousands of variants for multiple complex phenotypes, conventional statistical approaches can be limited by simplified assumptions such as linearity and lack of epistasis models. In this work, we trained artificial neural networks for predicting complex traits using both simulated and real genotype/phenotype datasets. We extracted feature importance scores via different post hoc interpretability methods to identify potentially associated loci (PAL) for the target phenotype. Simulations we performed with various parameters demonstrated that associated loci can be detected with good precision using strict selection criteria, but downstream analyses are required for fine-mapping the exact variants due to linkage disequilibrium, similarly to conventional GWAS. By applying our approach to the schizophrenia cohort in the Estonian Biobank, we were able to detect multiple PAL related to this highly polygenic and heritable disorder. We also performed enrichment analyses with PAL in genic regions, which predominantly identified terms associated with brain morphology. With further improvements in model optimization and confidence measures, artificial neural networks can enhance the identification of genomic loci associated with complex diseases, providing a more comprehensive approach for GWAS and serving as initial screening tools for subsequent functional studies.

Large Language Models (LLMs) have surged in popularity in recent months, but they have demonstrated concerning capabilities to generate harmful content when manipulated. While techniques like safety fine-tuning aim to minimize harmful use, recent works have shown that LLMs remain vulnerable to attacks that elicit toxic responses. In this work, we introduce the Proxy-Guided Attack on LLMs (PAL), the first optimization-based attack on LLMs in a black-box query-only setting. In particular, it relies on a surrogate model to guide the optimization and a sophisticated loss designed for real-world LLM APIs. Our attack achieves 84% attack success rate (ASR) on GPT-3.5-Turbo and 48% on Llama-2-7B, compared to 4% for the current state of the art. We also propose GCG++, an improvement to the GCG attack that reaches 94% ASR on white-box Llama-2-7B, and the Random-Search Attack on LLMs (RAL), a strong but simple baseline for query-based attacks. We believe the techniques proposed in this work will enable more comprehensive safety testing of LLMs and, in the long term, the development of better security guardrails. The code can be found at https://github.com/chawins/pal.

Chain-of-thought (CoT) prompting with large language models has proven effective in numerous natural language processing tasks, but designing prompts that generalize well to diverse problem types can be challenging, especially in the context of math word problem (MWP) solving. Additionally, it is common to have a large amount of training data that have a better diversity coverage but CoT annotations are not available, which limits the use of supervised learning techniques. To address these issues, we investigate two approaches to leverage the training data in a few-shot prompting scenario: dynamic program prompting and program distillation. Our approach is largely inspired by Gao et al., (2022), where they proposed to replace the CoT with the programs as the intermediate reasoning step. Such a prompting strategy allows us to accurately verify the answer correctness through program execution in MWP solving. Our dynamic program prompting involves annotating the training data by sampling correct programs from a large language model, while program distillation involves adapting a smaller model to the program-annotated training data. Our experiments on three standard MWP datasets demonstrate the effectiveness of these approaches, yielding significant improvements over previous baselines for prompting and fine-tuning. Our results suggest that leveraging a large amount of training data can improve the generalization ability of prompts and boost the performance of fine-tuned small models in MWP solving.