Ricardo Silva

Marrone Silvério Melo Dantas, Iago Richard Rodrigues, Assis Tiago Oliveira Filho et al.

IoT devices suffer from resource limitations, such as processor, RAM, and disc storage. These limitations become more evident when handling demanding applications, such as deep learning, well-known for their heavy computational requirements. A case in point is robot pose estimation, an application that predicts the critical points of the desired image object. One way to mitigate processing and storage problems is compressing that deep learning application. This paper proposes a new CNN for the pose estimation while applying the compression techniques of pruning and quantization to reduce his demands and improve the response time. While the pruning process reduces the total number of parameters required for inference, quantization decreases the precision of the floating-point. We run the approach using a pose estimation task for a robotic arm and compare the results in a high-end device and a constrained device. As metrics, we consider the number of Floating-point Operations Per Second(FLOPS), the total of mathematical computations, the calculation of parameters, the inference time, and the number of video frames processed per second. In addition, we undertake a qualitative evaluation where we compare the output image predicted for each pruned network with the corresponding original one. We reduce the originally proposed network to a 70% pruning rate, implying an 88.86% reduction in parameters, 94.45% reduction in FLOPS, and for the disc storage, we reduced the requirement in 70% while increasing error by a mere $1\%$. With regard input image processing, this metric increases from 11.71 FPS to 41.9 FPS for the Desktop case. When using the constrained device, image processing augmented from 2.86 FPS to 10.04 FPS. The higher processing rate of image frames achieved by the proposed approach allows a much shorter response time.

Kaican Li, Weiyan Xie, Yongxiang Huang et al.

Fine-tuning foundation models often compromises their robustness to distribution shifts. To remedy this, most robust fine-tuning methods aim to preserve the pre-trained features. However, not all pre-trained features are robust and those methods are largely indifferent to which ones to preserve. We propose dual risk minimization (DRM), which combines empirical risk minimization with worst-case risk minimization, to better preserve the core features of downstream tasks. In particular, we utilize core-feature descriptions generated by LLMs to induce core-based zero-shot predictions which then serve as proxies to estimate the worst-case risk. DRM balances two crucial aspects of model robustness: expected performance and worst-case performance, establishing a new state of the art on various real-world benchmarks. DRM significantly improves the out-of-distribution performance of CLIP ViT-L/14@336 on ImageNet (75.9 to 77.1), WILDS-iWildCam (47.1 to 51.8), and WILDS-FMoW (50.7 to 53.1); opening up new avenues for robust fine-tuning. Our code is available at https://github.com/vaynexie/DRM .

Jialin Yu, Yuxiang Zhou, Yulan He et al.

Adapting to latent-confounded shifts remains a core challenge in modern AI. These shifts are propagated via latent variables that induce spurious, non-transportable correlations between inputs and labels. One practical failure mode arises when fine-tuning pre-trained foundation models on confounded data (e.g., where certain text tokens or image backgrounds spuriously correlate with the label), leaving models vulnerable at deployment. We frame causal fine-tuning as an identification problem and pose an explicit causal model that decomposes inputs into low-level spurious features and high-level causal representations. Under this family of models, we formalize the assumptions required for identification. Using pre-trained language models as a case study, we show how identifying and adjusting these components during causal fine-tuning enables automatic adaptation to latent-confounded shifts at test time. Experiments on semi-synthetic benchmarks derived from real-world problems demonstrate that our method outperforms black-box domain generalization baselines, illustrating the benefits of explicitly modeling causal structure.

Jean Kaddour, Linqing Liu, Ricardo Silva et al.

Recently, flat-minima optimizers, which seek to find parameters in low-loss neighborhoods, have been shown to improve a neural network's generalization performance over stochastic and adaptive gradient-based optimizers. Two methods have received significant attention due to their scalability: 1. Stochastic Weight Averaging (SWA), and 2. Sharpness-Aware Minimization (SAM). However, there has been limited investigation into their properties and no systematic benchmarking of them across different domains. We fill this gap here by comparing the loss surfaces of the models trained with each method and through broad benchmarking across computer vision, natural language processing, and graph representation learning tasks. We discover several surprising findings from these results, which we hope will help researchers further improve deep learning optimizers, and practitioners identify the right optimizer for their problem.

Jacobo Roa-Vicens, Cyrine Chtourou, Angelos Filos et al.

Multi-agent learning is a promising method to simulate aggregate competitive behaviour in finance. Learning expert agents' reward functions through their external demonstrations is hence particularly relevant for subsequent design of realistic agent-based simulations. Inverse Reinforcement Learning (IRL) aims at acquiring such reward functions through inference, allowing to generalize the resulting policy to states not observed in the past. This paper investigates whether IRL can infer such rewards from agents within real financial stochastic environments: limit order books (LOB). We introduce a simple one-level LOB, where the interactions of a number of stochastic agents and an expert trading agent are modelled as a Markov decision process. We consider two cases for the expert's reward: either a simple linear function of state features; or a complex, more realistic non-linear function. Given the expert agent's demonstrations, we attempt to discover their strategy by modelling their latent reward function using linear and Gaussian process (GP) regressors from previous literature, and our own approach through Bayesian neural networks (BNN). While the three methods can learn the linear case, only the GP-based and our proposed BNN methods are able to discover the non-linear reward case. Our BNN IRL algorithm outperforms the other two approaches as the number of samples increases. These results illustrate that complex behaviours, induced by non-linear reward functions amid agent-based stochastic scenarios, can be deduced through inference, encouraging the use of inverse reinforcement learning for opponent-modelling in multi-agent systems.

Yin Cheng Ng, Ricardo Silva

We propose a dynamic edge exchangeable network model that can capture sparse connections observed in real temporal networks, in contrast to existing models which are dense. The model achieved superior link prediction accuracy on multiple data sets when compared to a dynamic variant of the blockmodel, and is able to extract interpretable time-varying community structures from the data. In addition to sparsity, the model accounts for the effect of social influence on vertices' future behaviours. Compared to the dynamic blockmodels, our model has a smaller latent space. The compact latent space requires a smaller number of parameters to be estimated in variational inference and results in a computationally friendly inference algorithm.