Search
Results
-
Parameter-Agnostic Optimization under Relaxed Smoothness
(2024)Tuning hyperparameters, such as the stepsize, presents a major challenge of training machine learning models. To address this challenge, numerous adaptive optimization algorithms have been developed that achieve near-optimal complexities, even when stepsizes are independent of problem-specific parameters, provided that the loss function is $L$-smooth. However, as the assumption is relaxed to the more realistic $(L_0, L_1)$-smoothness, all ...Conference Paper -
High-Accuracy and Energy-Efficient Acoustic Inference using Hardware-Aware Training and a 0.34nW/Ch Full-Wave Rectifier
(2023)2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS)A full-wave rectifier (FWR) is a necessary component of many analog acoustic feature extractor (FEx) designs targeted at edge audio applications. However, analog circuits that perform close-to-ideal rectification contribute a significant portion of the total power of the FEx. This work presents an energy-efficient FWR design by using a dynamic comparator and scaling the comparator clock frequency with its input signal bandwidth. Simulated ...Conference Paper -
Generalization Bounds of Nonconvex-(Strongly)-Concave Stochastic Minimax Optimization
(2024)This paper takes an initial step to systematically investigate the generalization bounds of algorithms for solving nonconvex-(strongly)-concave (NC-SC/NC-C) stochastic minimax optimization measured by the stationarity of primal functions. We first establish algorithm-agnostic generalization bounds via uniform convergence between the empirical minimax problem and the population minimax problem. The sample complexities for achieving ...Conference Paper -
A Fair and Resilient Decentralized Clock Network for Transaction Ordering
(2024)Leibniz International Proceedings in Informatics (LIPIcs) ~ 27th International Conference on Principles of Distributed Systems (OPODIS 2023)Traditional blockchain design gives miners or validators full control over transaction ordering, i.e., they can freely choose which transactions to include or exclude, as well as in which order. While not an issue initially, the emergence of decentralized finance has introduced new transaction order dependencies allowing parties in control of the ordering to make a profit by front-running others’ transactions. In this work, we present the ...Conference Paper -
Reducing Nearest Neighbor Training Sets Optimally and Exactly
(2023)Proceedings of the 35th Canadian Conference on Computational Geometry (CCCG 2023)In nearest-neighbor classification, a training set $P$ of points in $\mathbb{R}^d$ with given classification is used to classify every point in $\mathbb{R}^d$: Every point gets the same classification as its nearest neighbor in $P$. Recently, Eppstein [SOSA'22] developed an algorithm to detect the relevant training points, those points $p\in P$, such that $P$ and $P\setminus\{p\}$ induce different classifications. We investigate the problem ...Conference Paper -
On the depletion behaviour of low-temperature covalently bonded silicon sensor diodes
(2022)Journal of InstrumentationLow temperature covalent direct wafer-wafer bonding allows for the fusion of multiple semiconductor wafers without any additional material at the bonding interface. In the context of particle pixel detectors this might provide an alternative to bump-bonding for joining sensors to readout chips. Previous investigations have shown that the amorphous layer formed at the interface during bonding is detrimental to charge propagation. To ...Conference Paper -
DeFi and NFTs Hinder Blockchain Scalability
(2024)Lecture Notes in Computer Science ~ Financial Cryptography and Data SecurityMany classical blockchains are known to have an embarrassingly low transaction throughput, down to Bitcoin's notorious seven transactions per second limit. Various proposals and implementations for increasing throughput emerged in the first decade of blockchain research. But how much concurrency is possible? In their early days, blockchains were mostly used for simple transfers from user to user. More recently, however, decentralized ...Conference Paper -
Demystifying Web3 Centralization: The Case of Off-Chain NFT Hijacking
(2024)Lecture Notes in Computer Science ~ Financial Cryptography and Data SecurityDespite the ambitious vision of re-decentralizing the Web as we know it, the Web3 movement is facing many hurdles of centralization which seem insurmountable in the near future, and the security implications of centralization remain largely unexplored. Using non-fungible tokens (NFTs) as a case study, we conduct a systematic analysis of the threats posed by centralized entities in the current Web3 ecosystem. Our findings are concerning: ...Conference Paper -
3ET: Efficient Event-based Eye Tracking using a Change-Based ConvLSTM Network
(2023)2023 IEEE Biomedical Circuits and Systems Conference (BioCAS)This paper presents a sparse Change-Based Convolutional Long Short-Term Memory (CB-ConvLSTM) model for event-based eye tracking, key for next-generation wearable healthcare technology such as AR/VR headsets. We leverage the benefits of retina-inspired event cameras, namely their low-latency response and sparse output event stream, over traditional frame-based cameras. Our CB-ConvLSTM architecture efficiently extracts spatio-temporal ...Conference Paper -
Synaptic metaplasticity with multi-level memristive devices
(2023)2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS)Deep learning has made remarkable progress in various tasks, surpassing human performance in some cases. However, one drawback of neural networks is catastrophic forgetting, where a network trained on one task forgets the solution when learning a new one. To address this issue, recent works have proposed solutions based on Binarized Neural Networks (BNNs) incorporating metaplasticity. In this work, we extend this solution to quantized ...Conference Paper