_id,doi,title
14364,10.1137/20M1375851,Why extension-based proofs fail
14458,,SparseGPT: Massive language models can be accurately pruned in one-shot
14460,,SparseProp: Efficient sparse backpropagation for faster training of neural networks at the edge
14461,,Quantized distributed training of large models with convergence guarantees
14771,10.1109/cvpr52729.2023.02334,Bias in pruned vision models: In-depth analysis and countermeasures
13053,,CrAM: A Compression-Aware Minimizer
13074,10.15479/at:ista:13074,Efficiency and generalization of sparse neural networks
12566,10.1016/j.tcs.2023.113733,Wait-free approximate agreement on graphs
11180,10.1145/3503221.3508432,Multi-queues can be state-of-the-art priority schedulers
11183,10.4230/LIPIcs.OPODIS.2021.15,"Beyond distributed subgraph detection: Induced subgraphs, multicolored problems and graph parameters"
11184,10.4230/LIPIcs.OPODIS.2021.14,Fast graphical population protocols
11844,10.1145/3519270.3538435,Near-optimal leader election in population protocols on graphs
12299,10.1109/cvpr52688.2022.01195,How well do sparse ImageNet models transfer?
10854,10.1145/3410220.3453923,Input-dynamic distributed algorithms for communication networks
10855,10.1145/3447384,Input-dynamic distributed algorithms for communication networks
11436,,Asynchronous optimization methods for efficient training of deep neural networks with guarantees
11452,,Distributed principal component analysis with limited communication
11458,,AC/DC: Alternating Compressed/DeCompressed training of deep neural networks
11463,,M-FAC: Efficient matrix-free approximations of second-order information
11464,,Towards tight communication lower bounds for distributed optimisation