arXiv subjects

Sourav Ghosh

Publications and source records attributed to Sourav Ghosh.

At least 37 records · Page 2Linked to original sources

arXiv2024

Avatars of Margulis invariants and proper actions

In this article, we provide a necessary and sufficient criterion for proper actions on $\mathbb{H}^{n,n-1}$ in terms of certain special Anosov representations in $\mathsf{SO}(n,n)$. Moreover, we show that affine Anosov representations of any word hyperbolic group in $\mathsf{SO}(n,n-1)\ltimes\mathbb{R}^{2n-1}$ are infinitesimal versions of such special Anosov representations. Finally, using the above two results we interpret Margulis spacetimes as infinitesimal versions of quotient manifolds of $\mathbb{H}^{n,n-1}$. In the appendix, we give a description of the appropriate cross-ratios in our setting and their infinitesimal versions.

math.GT↗

arXiv2024

Affine Anosov representations

In this survey article we discuss about possible generalizations of Anosov representations in the affine setting and their consequences.

math.DS↗

arXiv2024

Deformation of Fuchsian representations and proper affine actions

The main goal of this article is to generalize Mess' work and using results from Labourie--Wentworth, Potrie--Sambarino and Smilga, to show that inside Hitchin representations, infinitesimal deformations of Fuchsian representations of a cocompact surface group do not act properly along the directions corresponding to the sum of a mixed odd differential and a $2m$-differential for any $1\leq m \leq \lfloor\frac{n}{2}\rfloor$. In the process, we introduce affine versions of cross ratios and triple ratios. We introduce Margulis invariants and relate them with affine crossratios and infinitesimal Jordan projections. We obtain a general equivalent criterion for existence of proper affine actions in terms of the structure of the Margulis invariant spectra. Also, using a stability argument we show the existence of proper affine actions of non-abelian free groups whose linear part is a Hitchin representation.

math.GT↗

arXiv2024

Task Planning for Object Rearrangement in Multi-room Environments

Object rearrangement in a multi-room setup should produce a reasonable plan that reduces the agent's overall travel and the number of steps. Recent state-of-the-art methods fail to produce such plans because they rely on explicit exploration for discovering unseen objects due to partial observability and a heuristic planner to sequence the actions for rearrangement. This paper proposes a novel hierarchical task planner to efficiently plan a sequence of actions to discover unseen objects and rearrange misplaced objects within an untidy house to achieve a desired tidy state. The proposed method introduces several novel techniques, including (i) a method for discovering unseen objects using commonsense knowledge from large language models, (ii) a collision resolution and buffer prediction method based on Cross-Entropy Method to handle blocked goal and swap cases, (iii) a directed spatial graph-based state space for scalability, and (iv) deep reinforcement learning (RL) for producing an efficient planner. The planner interleaves the discovery of unseen objects and rearrangement to minimize the number of steps taken and overall traversal of the agent. The paper also presents new metrics and a benchmark dataset called MoPOR to evaluate the effectiveness of the rearrangement planning in a multi-room setting. The experimental results demonstrate that the proposed method effectively addresses the multi-room rearrangement problem.

cs.RO↗

arXiv2024

What's in the Flow? Exploiting Temporal Motion Cues for Unsupervised Generic Event Boundary Detection

Generic Event Boundary Detection (GEBD) task aims to recognize generic, taxonomy-free boundaries that segment a video into meaningful events. Current methods typically involve a neural model trained on a large volume of data, demanding substantial computational power and storage space. We explore two pivotal questions pertaining to GEBD: Can non-parametric algorithms outperform unsupervised neural methods? Does motion information alone suffice for high performance? This inquiry drives us to algorithmically harness motion cues for identifying generic event boundaries in videos. In this work, we propose FlowGEBD, a non-parametric, unsupervised technique for GEBD. Our approach entails two algorithms utilizing optical flow: (i) Pixel Tracking and (ii) Flow Normalization. By conducting thorough experimentation on the challenging Kinetics-GEBD and TAPOS datasets, our results establish FlowGEBD as the new state-of-the-art (SOTA) among unsupervised methods. FlowGEBD exceeds the neural models on the Kinetics-GEBD dataset by obtaining an F1@0.05 score of 0.713 with an absolute gain of 31.7% compared to the unsupervised baseline and achieves an average F1 score of 0.623 on the TAPOS validation dataset.

cs.CV↗

arXiv2024

Margulis Multiverse: Infinitesimal Rigidity, Pressure Form and Convexity

In this article we construct the pressure form on the moduli space of higher dimensional Margulis spacetimes without cusps and study its properties. We show that the Margulis spacetimes are infinitesimally determined by their marked Margulis invariant spectrums. We use it to show that the restrictions of the pressure form give Riemannian metrics on the constant entropy sections of the quotient moduli space. We also show that constant entropy sections of the moduli space with fixed linear part bound convex domains.

math.GT↗

arXiv2024

Affine Anosov representations and proper actions

We define the notion of affine Anosov representations of word hyperbolic groups into the affine group $\mathsf{SO}^0(n+1,n)\ltimes\mathbb{R}^{2n+1}$. We then show that a representation $ρ$ of a word hyperbolic group is affine Anosov if and only if its linear part $\mathtt{L}_ρ$ is Anosov in $\mathsf{SO}^0(n+1,n)$ with respect to the stabilizer of a maximal isotropic plane and $ρ(Γ)$ acts properly on $\mathbb{R}^{2n+1}$.

math.GT↗

arXiv2024

TrICy: Trigger-guided Data-to-text Generation with Intent aware Attention-Copy

Data-to-text (D2T) generation is a crucial task in many natural language understanding (NLU) applications and forms the foundation of task-oriented dialog systems. In the context of conversational AI solutions that can work directly with local data on the user's device, architectures utilizing large pre-trained language models (PLMs) are impractical for on-device deployment due to a high memory footprint. To this end, we propose TrICy, a novel lightweight framework for an enhanced D2T task that generates text sequences based on the intent in context and may further be guided by user-provided triggers. We leverage an attention-copy mechanism to predict out-of-vocabulary (OOV) words accurately. Performance analyses on E2E NLG dataset (BLEU: 66.43%, ROUGE-L: 70.14%), WebNLG dataset (BLEU: Seen 64.08%, Unseen 52.35%), and our Custom dataset related to text messaging applications, showcase our architecture's effectiveness. Moreover, we show that by leveraging an optional trigger input, data-to-text generation quality increases significantly and achieves the new SOTA score of 69.29% BLEU for E2E NLG. Furthermore, our analyses show that TrICy achieves at least 24% and 3% improvement in BLEU and METEOR respectively over LLMs like GPT-3, ChatGPT, and Llama 2. We also demonstrate that in some scenarios, performance improvement due to triggers is observed even when they are absent in training.

cs.CL↗

arXiv2023

An Edge Assisted Robust Smart Traffic Management and Signalling System for Guiding Emergency Vehicles During Peak Hours

Congestion in traffic is an unavoidable circumstance in many cities in India and other countries. It is an issue of major concern. The steep rise in the number of automobiles on the roads followed by old infrastructure, accidents, pedestrian traffic, and traffic rule violations all add to challenging traffic conditions. Given these poor conditions of traffic, there is a critical need for automatically detecting and signaling systems. There are already various technologies that are used for traffic management and signaling systems like video analysis, infrared sensors, and wireless sensors. The main issue with these methods is they are very costly and high maintenance is required. In this paper, we have proposed a three-phase system that can guide emergency vehicles and manage traffic based on the degree of congestion. In the first phase, the system processes the captured images and calculates the Index value which is used to discover the degree of congestion. The Index value of a particular road depends on its width and the length up to which the camera captures images of that road. We have to take input for the parameters (length and width) while setting up the system. In the second phase, the system checks whether there are any emergency vehicles present or not in any lane. In the third phase, the whole processing and decision-making part is performed at the edge server. The proposed model is robust and it takes into consideration adverse weather conditions such as hazy, foggy, and windy. It works very efficiently in low light conditions also. The edge server is a strategically placed server that provides us with low latency and better connectivity. Using Edge technology in this traffic management system reduces the strain on cloud servers and the system becomes more reliable in real-time because the latency and bandwidth get reduced due to processing at the intermediate edge server.

cs.CV↗

arXiv2022

eDWaaS: A Scalable Educational Data Warehouse as a Service

The university management is perpetually in the process of innovating policies to improve the quality of service. Intellectual growth of the students, the popularity of university are some of the major areas that management strives to improve upon. Relevant historical data is needed in support of taking any decision. Furthermore, providing data to various university ranking frameworks is a frequent activity in recent years. The format of such requirement changes frequently which requires efficient manual effort. Maintaining a data warehouse can be a solution to this problem. However, both in-house and outsourced implementation of a dedicated data warehouse may not be a cost-effective and smart solution. This work proposes an educational data warehouse as a service (eDWaaS) model to store historical data for multiple universities. The proposed multi-tenant schema facilitates the universities to maintain their data warehouse in a cost-effective solution. It also addresses the scalability issues in implementing such data warehouse as a service model.

cs.DB↗

arXiv2022

LIP: Lightweight Intelligent Preprocessor for meaningful text-to-speech

Existing Text-to-Speech (TTS) systems need to read messages from the email which may have Personal Identifiable Information (PII) to text messages that can have a streak of emojis and punctuation. 92% of the world's online population use emoji with more than 10 billion emojis sent everyday. Lack of preprocessor leads to messages being read as-is including punctuation and infographics like emoticons. This problem worsens if there is a continuous sequence of punctuation/emojis that are quite common in real-world communications like messaging, Social Networking Site (SNS) interactions, etc. In this work, we aim to introduce a lightweight intelligent preprocessor (LIP) that can enhance the readability of a message before being passed downstream to existing TTS systems. We propose multiple sub-modules including: expanding contraction, censoring swear words, and masking of PII, as part of our preprocessor to enhance the readability of text. With a memory footprint of only 3.55 MB and inference time of 4 ms for up to 50-character text, our solution is suitable for real-time deployment. This work being the first of its kind, we try to benchmark with an open independent survey, the result of which shows 76.5% preference towards LIP enabled TTS engine as compared to standard TTS.

cs.CL↗

arXiv2022

PrivPAS: A real time Privacy-Preserving AI System and applied ethics

With 3.78 billion social media users worldwide in 2021 (48% of the human population), almost 3 billion images are shared daily. At the same time, a consistent evolution of smartphone cameras has led to a photography explosion with 85% of all new pictures being captured using smartphones. However, lately, there has been an increased discussion of privacy concerns when a person being photographed is unaware of the picture being taken or has reservations about the same being shared. These privacy violations are amplified for people with disabilities, who may find it challenging to raise dissent even if they are aware. Such unauthorized image captures may also be misused to gain sympathy by third-party organizations, leading to a privacy breach. Privacy for people with disabilities has so far received comparatively less attention from the AI community. This motivates us to work towards a solution to generate privacy-conscious cues for raising awareness in smartphone users of any sensitivity in their viewfinder content. To this end, we introduce PrivPAS (A real time Privacy-Preserving AI System) a novel framework to identify sensitive content. Additionally, we curate and annotate a dataset to identify and localize accessibility markers and classify whether an image is sensitive to a featured subject with a disability. We demonstrate that the proposed lightweight architecture, with a memory footprint of a mere 8.49MB, achieves a high mAP of 89.52% on resource-constrained devices. Furthermore, our pipeline, trained on face anonymized data, achieves an F1-score of 73.1%.

cs.CV↗

arXiv2021

LIDSNet: A Lightweight on-device Intent Detection model using Deep Siamese Network

Intent detection is a crucial task in any Natural Language Understanding (NLU) system and forms the foundation of a task-oriented dialogue system. To build high-quality real-world conversational solutions for edge devices, there is a need for deploying intent detection model on device. This necessitates a light-weight, fast, and accurate model that can perform efficiently in a resource-constrained environment. To this end, we propose LIDSNet, a novel lightweight on-device intent detection model, which accurately predicts the message intent by utilizing a Deep Siamese Network for learning better sentence representations. We use character-level features to enrich the sentence-level representations and empirically demonstrate the advantage of transfer learning by utilizing pre-trained embeddings. Furthermore, to investigate the efficacy of the modules in our architecture, we conduct an ablation study and arrive at our optimal model. Experimental results prove that LIDSNet achieves state-of-the-art competitive accuracy of 98.00% and 95.97% on SNIPS and ATIS public datasets respectively, with under 0.59M parameters. We further benchmark LIDSNet against fine-tuned BERTs and show that our model is at least 41x lighter and 30x faster during inference than MobileBERT on Samsung Galaxy S20 device, justifying its efficiency on resource-constrained edge devices.

cs.CL↗

arXiv2021

Measuring Domain Knowledge for Early Prediction of Student Performance: A Semantic Approach

The growing popularity of data mining catalyses the researchers to explore various exciting aspects of education. Early prediction of student performance is an emerging area among them. The researchers have used various predictors in performance modelling studies. Although prior cognition can affect student performance, establishing their relationship is still an open research challenge. Quantifying the knowledge from readily available data is the major challenge here. We have proposed a semantic approach for this purpose. Association mining on nearly 0.35 million observations establishes that prior cognition impacts the student performance. The proposed approach of measuring domain knowledge can help the early performance modelling studies to use it as a predictor.

cs.CY↗

arXiv2021

Finite step Rigidity of Hitchin representations and special Margulis-Smilga spacetimes

In this article we use the "escape from subvarieties lemma" introduced by Eskin--Mozes--Oh to prove finite step rigidity results for the Jordan-Lyapunov projection spectra of Hitchin representations and the Margulis-Smilga invariant spectra of some special Margulis-Smilga spacetimes. In the process, we also prove a similar finite step rigidity result for the Cartan spectra of representations of a finitely generated group inside a connected semisimple real algebraic Lie group with trivial center.

math.GT↗

arXiv2021

LiteMuL: A Lightweight On-Device Sequence Tagger using Multi-task Learning

Named entity detection and Parts-of-speech tagging are the key tasks for many NLP applications. Although the current state of the art methods achieved near perfection for long, formal, structured text there are hindrances in deploying these models on memory-constrained devices such as mobile phones. Furthermore, the performance of these models is degraded when they encounter short, informal, and casual conversations. To overcome these difficulties, we present LiteMuL - a lightweight on-device sequence tagger that can efficiently process the user conversations using a Multi-Task Learning (MTL) approach. To the best of our knowledge, the proposed model is the first on-device MTL neural model for sequence tagging. Our LiteMuL model is about 2.39 MB in size and achieved an accuracy of 0.9433 (for NER), 0.9090 (for POS) on the CoNLL 2003 dataset. The proposed LiteMuL not only outperforms the current state of the art results but also surpasses the results of our proposed on-device task-specific models, with accuracy gains of up to 11% and model-size reduction by 50%-56%. Our model is competitive with other MTL approaches for NER and POS tasks while outshines them with a low memory footprint. We also evaluated our model on custom-curated user conversations and observed impressive results.

cs.CL↗

arXiv2021

edATLAS: An Efficient Disambiguation Algorithm for Texting in Languages with Abugida Scripts

Abugida refers to a phonogram writing system where each syllable is represented using a single consonant or typographic ligature, along with a default vowel or optional diacritic(s) to denote other vowels. However, texting in these languages has some unique challenges in spite of the advent of devices with soft keyboard supporting custom key layouts. The number of characters in these languages is large enough to require characters to be spread over multiple views in the layout. Having to switch between views many times to type a single word hinders the natural thought process. This prevents popular usage of native keyboard layouts. On the other hand, supporting romanized scripts (native words transcribed using Latin characters) with language model based suggestions is also set back by the lack of uniform romanization rules. To this end, we propose a disambiguation algorithm and showcase its usefulness in two novel mutually non-exclusive input methods for languages natively using the abugida writing system: (a) disambiguation of ambiguous input for abugida scripts, and (b) disambiguation of word variants in romanized scripts. We benchmark these approaches using public datasets, and show an improvement in typing speed by 19.49%, 25.13%, and 14.89%, in Hindi, Bengali, and Thai, respectively, using Ambiguous Input, owing to the human ease of locating keys combined with the efficiency of our inference method. Our Word Variant Disambiguation (WDA) maps valid variants of romanized words, previously treated as Out-of-Vocab, to a vocabulary of 100k words with high accuracy, leading to an increase in Error Correction F1 score by 10.03% and Next Word Prediction (NWP) by 62.50% on average.

cs.CL↗

arXiv2021

Comparison of the electrochemical performance of CeO2 and rare earth-based mixed metallic oxide (Ce0.9Zr0.1O2) for supercapacitor applications

CeO2 and Ce0.9Zr0.1O2 are prepared from the sol-gel method to investigate and compare their electrochemical properties for supercapacitor applications. Structural, morphological, and elemental studies have been done for CeO2 and Ce0.9Zr0.1O2 by XRD, SEM, and EDX. Cyclic voltammetry, galvanostatic charge-discharge, and electrochemical impedance spectroscopy techniques are used to study the electrochemical performance of these materials. Doping enhances the electrochemical performance of the electrode, by improving the specific capacitance (~150%, 243 F g-1 from 96 F g-1) for the doped system @2 mV s-1 Vs. Ag/AgCl reference electrode in 2 mol L-1 KOH electrolyte solution. Ce0.9Zr0.1O2 shows only ~30% of capacitance degradation for a ten folds increase in current densities. Ce0.9Zr0.1O2 also shows 16% capacitance degradation after 800 cycles with excellent Columbic efficiency (~100%) @2 A g-1 current density. Partial replacement of Ce4+ ion (0.97 Å) with Zr4+ ion (0.84 Å) results in a decrease in lattice parameter, as confirmed by Rietveld refinement. Ce0.9Zr0.1O2 has provided good energy, and power density of 1.128 Wh kg-1and 112.5 W kg-1 respectively. Furthermore, better diffusivity of the Ce0.9Zr0.1O2 in KOH electrolyte (indicated using Randles-Sevcik equation-based analysis) is correlated with better electrochemical performance. These insights presented here clearly indicate that Zr doping into CeO2 results in a promising candidate material for electrochemical and supercapacitive applications.

cond-mat.mtrl-sci↗