Author name cluster

Sameera Ramasinghe

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

15 papers

2 author rows

TMLR Journal 2025 Journal Article

LumiNet: Perception-Driven Knowledge Distillation via Statistical Logit Calibration

Md. Ismail Hossain
M M Lutfe Elahi
Sameera Ramasinghe
Ali Cheraghian
Fuad Rahman
Nabeel Mohammed
Shafin Rahman

In the knowledge distillation literature, feature-based methods have dominated due to their ability to effectively tap into extensive teacher models. In contrast, logit-based approaches, which aim to distill `dark knowledge' from teachers, typically exhibit inferior performance compared to feature-based methods. To bridge this gap, we present LumiNet, a novel knowledge distillation algorithm designed to enhance logit-based distillation. We introduce the concept of `perception', aiming to calibrate logits based on the model's representation capability. This concept addresses overconfidence issues in the logit-based distillation method while also introducing a novel method to distill knowledge from the teacher. It reconstructs the logits of a sample/instances by considering relationships with other samples in the batch. LumiNet excels on benchmarks like CIFAR-100, ImageNet, and MSCOCO, outperforming the leading feature-based methods, e.g., compared to KD with ResNet18 and MobileNetV2 on ImageNet, it shows improvements of 1.5\% and 2.05\%, respectively.

PDF Details

NeurIPS Conference 2025 Conference Paper

Mixtures of Subspaces for Bandwidth Efficient Context Parallel Training

Sameera Ramasinghe
Thalaiyasingam Ajanthan
Hadi Mohaghegh Dolatabadi
Gil Avraham
Violetta Shevchenko
Yan Zuo
Chamin P Hewa Koneputugodage
Alexander Long

Pretraining language models with extended context windows enhances their ability to leverage rich information during generation. Existing methods split input sequences into chunks, broadcast them across multiple devices, and compute attention block by block which incurs significant communication overhead. While feasible in high-speed clusters, these methods are impractical for decentralized training over low-bandwidth connections. We propose a compression method for communication-efficient context parallelism in decentralized settings, achieving a remarkable compression rate of over 95% with negligible overhead and no loss in convergence. Our key insight is to exploit the intrinsic low-rank structure of activation outputs by dynamically constraining them to learned mixtures of subspaces via efficient reparameterizations. We demonstrate scaling billion-parameter decentralized models to context lengths exceeding 100K tokens on networks as slow as 300Mbps, matching the wall-clock convergence speed of centralized models on 100Gbps interconnects.

PDF Details

ICML Conference 2025 Conference Paper

Nesterov Method for Asynchronous Pipeline Parallel Optimization

Thalaiyasingam Ajanthan
Sameera Ramasinghe
Yan Zuo
Gil Avraham
Alexander Long

Pipeline Parallelism (PP) enables large neural network training on small, interconnected devices by splitting the model into multiple stages. To maximize pipeline utilization, asynchronous optimization is appealing as it offers 100% pipeline utilization by construction. However, it is inherently challenging as the weights and gradients are no longer synchronized, leading to stale (or delayed) gradients. To alleviate this, we introduce a variant of Nesterov Accelerated Gradient (NAG) for asynchronous optimization in PP. Specifically, we modify the look-ahead step in NAG to effectively address the staleness in gradients. We theoretically prove that our approach converges at a sublinear rate in the presence of fixed delay in gradients. Our experiments on large-scale language modelling tasks using decoder-only architectures with up to 1B parameters, demonstrate that our approach significantly outperforms existing asynchronous methods, even surpassing the synchronous baseline.

Details

NeurIPS Conference 2025 Conference Paper

Subspace Networks: Scaling Decentralized Training with Communication-Efficient Model Parallelism

Sameera Ramasinghe
Thalaiyasingam Ajanthan
Gil Avraham
Yan Zuo
Alexander Long

Scaling models has led to significant advancements in deep learning, but training these models in decentralized settings remains challenging due to communication bottlenecks. While existing compression techniques are effective in data-parallel, they do not extend to model parallelism. Unlike data-parallel training, where weight gradients are exchanged, model-parallel requires compressing activations and activation gradients as they propagate through layers, accumulating compression errors. We propose a novel compression algorithm that compresses both forward and backward passes, enabling up to 99% compression with no convergence degradation with negligible memory/compute overhead. By leveraging a recursive structure in transformer networks, we predefine a low-dimensional subspace to confine the activations and gradients, allowing full reconstruction in subsequent layers. Our method achieves up to 100x improvement in communication efficiency and enables training billion-parameter-scale models over low-end GPUs connected via consumer-grade internet speeds as low as 80Mbps, matching the convergence of centralized datacenter systems with 100Gbps connections with model parallel.

PDF Details

NeurIPS Conference 2025 Conference Paper

Unextractable Protocol Models: Collaborative Training and Inference without Weight Materialization

Alexander Long
Chamin P Hewa Koneputugodage
Thalaiyasingam Ajanthan
Yan Zuo
Gil Avraham
Violetta Shevchenko
Hadi Mohaghegh Dolatabadi
Sameera Ramasinghe

We consider a decentralized setup in which the participants collaboratively train and serve a large neural network, and where each participant only processes a subset of the model. In this setup, we explore the possibility of unmaterializable weights, where a full weight set is never available to any one participant. We introduce Unextractable Protocol Models (UPMs): a training and inference framework that leverages the sharded model setup to ensure model shards (i. e. ,, subsets) held by participants are incompatible at different time steps. UPMs periodically inject time-varying, random, invertible transforms at participant boundaries; preserving the overall network function yet rendering cross-time assemblies incoherent. On Qwen-2. 5-0. 5B and Llama-3. 2-1B, 10 000 transforms leave FP32 perplexity unchanged ($\Delta$PPL$< 0. 01$; Jensen–Shannon drift $<4 \times 10^{-5}$), and we show how to control growth for lower precision datatypes. Applying a transform every 30s adds 3% latency, 0. 1% bandwidth, and 10% GPU-memory overhead at inference, while training overhead falls to 1. 6% time and < 1% memory. We consider several attacks, showing that the requirements of direct attacks are impractical and easy to defend against, and that gradient-based fine-tuning of stitched partitions consumes $\geq 60\%$ of the tokens required to train from scratch. By enabling models to be collaboratively trained yet not extracted, UPMs make it practical to embed programmatic incentive mechanisms in community-driven decentralized training.

PDF Details

ICML Conference 2024 Conference Paper

A sampling theory perspective on activations for implicit neural representations

Hemanth Saratchandran
Sameera Ramasinghe
Violetta Shevchenko
Alexander Long
Simon Lucey

Implicit Neural Representations (INRs) have gained popularity for encoding signals as compact, differentiable entities. While commonly using techniques like Fourier positional encodings or non-traditional activation functions (e. g. , Gaussian, sinusoid, or wavelets) to capture high-frequency content, their properties lack exploration within a unified theoretical framework. Addressing this gap, we conduct a comprehensive analysis of these activations from a sampling theory perspective. Our investigation reveals that, especially in shallow INRs, $\mathrm{sinc}$ activations—previously unused in conjunction with INRs—are theoretically optimal for signal encoding. Additionally, we establish a connection between dynamical systems and INRs, leveraging sampling theory to bridge these two paradigms.

Details

AAAI Conference 2024 Conference Paper

BLiRF: Bandlimited Radiance Fields for Dynamic Scene Modeling

Sameera Ramasinghe
Violetta Shevchenko
Gil Avraham
Anton van den Hengel

Inferring the 3D structure of a non-rigid dynamic scene from a single moving camera is an under-constrained problem. Inspired by the remarkable progress of neural radiance fields (NeRFs) in photo-realistic novel view synthesis of static scenes, it has also been extended to dynamic settings. Such methods heavily rely on implicit neural priors to regularize the problem. In this work, we take a step back and investigate how current implementations may entail deleterious effects including limited expressiveness, entanglement of light and density fields, and sub-optimal motion localization. Further, we devise a factorisation-based framework that represents the scene as a composition of bandlimited, high-dimensional signals. We demonstrate compelling results across complex dynamic scenes that involve changes in lighting, texture and long-range dynamics.

PDF Details DOI

ICLR Conference 2024 Conference Paper

Improving the Convergence of Dynamic NeRFs via Optimal Transport

Sameera Ramasinghe
Violetta Shevchenko
Gil Avraham
Hisham Husain
Anton van den Hengel

Synthesizing novel views for dynamic scenes from a collection of RGB inputs poses significant challenges due to the inherent under-constrained nature of the problem. To mitigate this ill-posedness, practitioners in the field of neural radiance fields (NeRF) often resort to the adoption of intricate geometric regularization techniques, including scene flow, depth estimation, or learned perceptual similarity. While these geometric cues have demonstrated their effectiveness, their incorporation leads to evaluation of computationally expensive off-the-shelf models, introducing substantial computational overhead into the pipeline. Moreover, seamlessly integrating such modules into diverse dynamic NeRF models can be a non-trivial task, hindering their utilization in an architecture-agnostic manner. In this paper, we propose a theoretically grounded, lightweight regularizer by treating the dynamics of a time-varying scene as a low-frequency change of a probability distribution of the light intensity. We constrain the dynamics of this distribution using optimal transport (OT) and provide error bounds under reasonable assumptions. Our regularization is learning-free, architecture agnostic, and can be implemented with just a few lines of code. Finally, we demonstrate the practical efficacy of our regularizer across state-of-the-art architectures.

Details

NeurIPS Conference 2024 Conference Paper

Neural Experts: Mixture of Experts for Implicit Neural Representations

Yizhak Ben-Shabat
Chamin Hewa Koneputugodage
Sameera Ramasinghe
Stephen Gould

Implicit neural representations (INRs) have proven effective in various tasks including image, shape, audio, and video reconstruction. These INRs typically learn the implicit field from sampled input points. This is often done using a single network for the entire domain, imposing many global constraints on a single function. In this paper, we propose a mixture of experts (MoE) implicit neural representation approach that enables learning local piece-wise continuous functions that simultaneously learns to subdivide the domain and fit it locally. We show that incorporating a mixture of experts architecture into existing INR formulations provides a boost in speed, accuracy, and memory requirements. Additionally, we introduce novel conditioning and pretraining methods for the gating network that improves convergence to the desired solution. We evaluate the effectiveness of our approach on multiple reconstruction tasks, including surface reconstruction, image reconstruction, and audio signal reconstruction and show improved performance compared to non-MoE methods. Code is available at our project page https: //sitzikbs. github. io/neural-experts-projectpage/.

PDF Details DOI

AAAI Conference 2023 Conference Paper

A Learnable Radial Basis Positional Embedding for Coordinate-MLPs

Sameera Ramasinghe
Simon Lucey

We propose a novel method to enhance the performance of coordinate-MLPs (also referred to as neural fields) by learning instance-specific positional embeddings. End-to-end optimization of positional embedding parameters along with network weights leads to poor generalization performance. Instead, we develop a generic framework to learn the positional embedding based on the classic graph-Laplacian regularization, which can implicitly balance the trade-off between memorization and generalization. This framework is then used to propose a novel positional embedding scheme, where the hyperparameters are learned per coordinate (i.e instance) to deliver optimal performance. We show that the proposed embedding achieves better performance with higher stability compared to the well-established random Fourier features (RFF). Further, we demonstrate that the proposed embedding scheme yields stable gradients, enabling seamless integration into deep architectures as intermediate layers.

PDF Details DOI

ICML Conference 2023 Conference Paper

How much does Initialization Affect Generalization?

Sameera Ramasinghe
Lachlan Ewen MacDonald
Moshiur R. Farazi
Hemanth Saratchandran
Simon Lucey

Characterizing the remarkable generalization properties of over-parameterized neural networks remains an open problem. A growing body of recent literature shows that the bias of stochastic gradient descent (SGD) and architecture choice implicitly leads to better generalization. In this paper, we show on the contrary that, independently of architecture, SGD can itself be the cause of poor generalization if one does not ensure good initialization. Specifically, we prove that any differentiably parameterized model, trained under gradient flow, obeys a weak spectral bias law which states that sufficiently high frequencies train arbitrarily slowly. This implies that very high frequencies present at initialization will remain after training, and hamper generalization. Further, we empirically test the developed theoretical insights using practical, deep networks. Finally, we contrast our framework with that supplied by the flat-minima conjecture and show that Fourier analysis grants a more reliable framework for understanding the generalization of neural networks.

Details

NeurIPS Conference 2022 Conference Paper

On the Frequency-bias of Coordinate-MLPs

Sameera Ramasinghe
Lachlan E. MacDonald
Simon Lucey

We show that typical implicit regularization assumptions for deep neural networks (for regression) do not hold for coordinate-MLPs, a family of MLPs that are now ubiquitous in computer vision for representing high-frequency signals. Lack of such implicit bias disrupts smooth interpolations between training samples, and hampers generalizing across signal regions with different spectra. We investigate this behavior through a Fourier lens and uncover that as the bandwidth of a coordinate-MLP is enhanced, lower frequencies tend to get suppressed unless a suitable prior is provided explicitly. Based on these insights, we propose a simple regularization technique that can mitigate the above problem, which can be incorporated into existing networks without any architectural modifications.

PDF Details

ICLR Conference 2021 Conference Paper

Conditional Generative Modeling via Learning the Latent Space

Sameera Ramasinghe
Kanchana Ranasinghe
Salman H. Khan 0001
Nick Barnes
Stephen Gould

Although deep learning has achieved appealing results on several machine learning tasks, most of the models are deterministic at inference, limiting their application to single-modal settings. We propose a novel general-purpose framework for conditional generation in multimodal spaces, that uses latent variables to model generalizable learning patterns while minimizing a family of regression cost functions. At inference, the latent variables are optimized to find solutions corresponding to multiple output modes. Compared to existing generative solutions, our approach demonstrates faster and more stable convergence, and can learn better representations for downstream tasks. Importantly, it provides a simple generic model that can perform better than highly engineered pipelines tailored using domain expertise on a variety of tasks, while generating diverse outputs. Code available at https://github.com/samgregoost/cGML.

Details

NeurIPS Conference 2021 Conference Paper

Rethinking conditional GAN training: An approach using geometrically structured latent manifolds

Sameera Ramasinghe
Moshiur Farazi
Salman H Khan
Nick Barnes
Stephen Gould

Conditional GANs (cGAN), in their rudimentary form, suffer from critical drawbacks such as the lack of diversity in generated outputs and distortion between the latent and output manifolds. Although efforts have been made to improve results, they can suffer from unpleasant side-effects such as the topology mismatch between latent and output spaces. In contrast, we tackle this problem from a geometrical perspective and propose a novel training mechanism that increases both the diversity and the visual quality of a vanilla cGAN, by systematically encouraging a bi-lipschitz mapping between the latent and the output manifolds. We validate the efficacy of our solution on a baseline cGAN (i. e. , Pix2Pix) which lacks diversity, and show that by only modifying its training mechanism (i. e. , with our proposed Pix2Pix-Geo), one can achieve more diverse and realistic outputs on a broad set of image-to-image translation tasks.

PDF Details

IROS Conference 2020 Conference Paper

Spectral-GANs for High-Resolution 3D Point-cloud Generation

Sameera Ramasinghe
Salman H. Khan 0001
Nick Barnes
Stephen Gould

Point-clouds are a popular choice for robotics and computer vision tasks due to their accurate shape description and direct acquisition from range-scanners. This demands the ability to synthesize and reconstruct high-quality point-clouds. Current deep generative models for 3D data generally work on simplified representations (e. g. , voxelized objects) and cannot deal with the inherent redundancy and irregularity in point-clouds. A few recent efforts on 3D point-cloud generation offer limited resolution and their complexity grows with the increase in output resolution. In this paper, we develop a principled approach to synthesize 3D point-clouds using a spectral-domain Generative Adversarial Network (GAN). Our spectral representation is highly structured and allows us to disentangle various frequency bands such that the learning task is simplified for a GAN model. As compared to spatial-domain generative approaches, our formulation allows us to generate high-resolution point-clouds with minimal computational overhead. Furthermore, we propose a fully differentiable block to transform from the spectral to the spatial domain and back, thereby allowing us to integrate knowledge from well-established spatial models. We demonstrate that Spectral-GAN performs well for point-cloud generation task. Additionally, it can learn a highly discriminative representation in an unsupervised fashion and can be used to accurately reconstruct 3D objects. Our codes are available at https://github.com/samgregoost/Spectral-GAN/.

Details