Related papers: Optimal Neural Summarisation for Full-Field Weak L…
Bayesian optimization (BO) is a model-based approach to sequentially optimize expensive black-box functions, such as the validation error of a deep neural network with respect to its hyperparameters. In many real-world scenarios, the…
Likelihood-free inference provides a rigorous approach to preform Bayesian analysis using forward simulations only. The main advantage of likelihood-free methods is its ability to account for complex physical processes and observational…
Recent advances in probabilistic deep learning enable efficient amortized Bayesian inference in settings where the likelihood function is only implicitly defined by a simulation program (simulation-based inference; SBI). But how faithful is…
Recently, compressive text summarisation offers a balance between the conciseness issue of extractive summarisation and the factual hallucination issue of abstractive summarisation. However, most existing compressive summarisation methods…
Various multi-instance learning (MIL) based approaches have been developed and successfully applied to whole-slide pathological images (WSI). Existing MIL methods emphasize the importance of feature aggregators, but largely neglect the…
We introduce two synthetic likelihood methods for Simulation-Based Inference (SBI), to conduct either amortized or targeted inference from experimental observations when a high-fidelity simulator is available. Both methods learn a…
Brain decoding is a field of computational neuroscience that uses measurable brain activity to infer mental states or internal representations of perceptual inputs. Therefore, we propose a novel approach to brain decoding that also relies…
Magnetic Resonance Imaging (MRI) represents an important diagnostic modality; however, its inherently slow acquisition process poses challenges in obtaining fully-sampled $k$-space data under motion. In the absence of fully-sampled…
Black-box simulators are widely used in robotics, but optimizing their parameters remains challenging due to inaccessible likelihoods. Simulation-Based Inference (SBI) tackles this issue using simulation-driven approaches, estimating the…
Weak lensing mass-mapping is a useful tool to access the full distribution of dark matter on the sky, but because of intrinsic galaxy ellipticies and finite fields/missing data, the recovery of dark matter maps constitutes a challenging…
Reinforcement learning with evaluation metrics as rewards is widely used to enhance specific capabilities of language models. However, for tasks such as factually consistent summarisation, existing metrics remain underdeveloped, limiting…
We investigate the accuracy of weak lensing simulations by comparing the results of five independently developed lensing simulation codes run on the same input $N$-body simulation. Our comparison focuses on the lensing convergence maps…
Using only image-sentence pairs, weakly-supervised visual-textual grounding aims to learn region-phrase correspondences of the respective entity mentions. Compared to the supervised approach, learning is more difficult since bounding boxes…
Convolutional Neural Networks (CNN) have recently been demonstrated on synthetic data to improve upon the precision of cosmological inference. In particular they have the potential to yield more precise cosmological constraints from weak…
Recent medical imaging studies have given rise to distinct but inter-related datasets corresponding to multiple experimental tasks or longitudinal visits. Standard scalar-on-image regression models that fit each dataset separately are not…
Weak-lensing peak counts provide a straightforward way to constrain cosmology by linking local maxima of the lensing signal to the mass function. Recent applications to data have already been numerous and fruitful. However, the importance…
Bayesian statistical inference loses predictive optimality when generative models are misspecified. Working within an existing coherent loss-based generalisation of Bayesian inference, we show existing Modular/Cut-model inference is…
The statistical power of weak lensing measurements is principally driven by the number of high redshift galaxies whose shapes are resolved. Conventional wisdom and physical intuition suggest this is optimised by deep imaging at long (red or…
We demonstrate a method for reconstructing the weak lensing potential from the Lyman-$\alpha$ forest data. We derive an optimal estimator for the lensing potential on the sky based on the correlation between pixels in real space. This…
The learning objective plays a fundamental role to build a recommender system. Most methods routinely adopt either pointwise or pairwise loss to train the model parameters, while rarely pay attention to softmax loss due to its computational…