ABCDEFGHIJKLMNOPQRSTUVWXYZAA
1
Make sure your assignments are done by March 11th!
2
InstructorPresenter
Topic (See second sheet for the classifications)
Paper title - 2021Web link for the PDF
3
4
Volkan Cevher
5
1Reinforcement LearningLogistic Q-Learninghttps://arxiv.org/abs/2010.11151
6
2Reinforcement LearningEfficiently Solving MDPs with Stochastic Mirror Descenthttp://proceedings.mlr.press/v119/jin20f.html
7
3Reinforcement LearningOn the Global Convergence Rates of Softmax Policy Gradient Methodshttp://proceedings.mlr.press/v119/mei20b/mei20b.pdf
8
4Reinforcement LearningFinite Sample Analysis of Two-Time-Scale Natural Actor-Critic Algorithmhttps://arxiv.org/pdf/2101.10506.pdf
9
5Reinforcement LearningRobust Reinforcement Learning via Adversarial training with Langevin Dynamicshttps://arxiv.org/abs/2002.06063
10
6Eunji ShinReinforcement LearningChoice of the presenter. Contact volkan.cevher@epfl.ch with your suggestion on an RL topic. Suggested topics: Inverse RL, Imitation Learning, Behavior cloning, Reward Shaping,
Other presenters for this choice can list themselves here --->
11
12
Pascal Frossard
13
1Tianzong ZhangNNWhat do neural networks learn when trained with random labels? https://arxiv.org/abs/2006.10455
14
2NNSE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkshttps://arxiv.org/pdf/2006.10503.pdf
15
3Benoît DenkingerNNGenerative Models as Distributions of Functionshttps://arxiv.org/pdf/2102.04776.pdf
16
4Lingjing KongRobust MLFast is better than free: Revisiting adversarial traininghttp://arxiv.org/abs/2001.03994
17
5Ines HaymannGraph NNLearning to Simulate Complex Physics with Graph Networkshttps://arxiv.org/pdf/2002.09405.pdf
18
19
Martin Jaggi
20
1Florian HaselbeckMeta-learningMeta-learning Transferable Representations with a Single Target Domainhttps://arxiv.org/abs/2011.01418
21
2Rabeeh Karimi MahabadiNLP The Power of Scale for Parameter-Efficient Prompt Tuninghttps://arxiv.org/pdf/2104.08691.pdf
22
3Ali MomeniDistributed MLRobust P2P Personalized Learninghttps://doi.org/10.1109/SRDS51746.2020.00037
23
4Prabhu Teja SivaprasadSGDFast convergence of stochastic subgradient method under interpolationhttps://openreview.net/forum?id=w2mYg3d0eot
24
5Sina SajadmaneshPrivate MLDifferentially Private Learning Needs Better Features (or Much More Data)https://openreview.net/pdf?id=YTWGvpFOQD-
25
26
Nicolas Flammarion
27
1Tianzong ZhangNeural NetworksWhat Do Neural Networks Learn When Trained With Random Labels?https://arxiv.org/pdf/2006.10455.pdf
28
2Apostolos ModasRobust MLAdversarial Weight Perturbation Helps Robust Generalization
https://proceedings.neurips.cc/paper/2020/file/1ef91c212e30e14bf125e9374262401f-Paper.pdf
29
3Seyed Mohammad Mahdi JohariNeural NetworksSharpness-aware Minimization for Efficiently Improving Generalizationhttps://openreview.net/forum?id=6Tm1mposlrM
30
4Samuel BeuretLangevinThe Langevin Monte Carlo algorithm in the non-smooth log-concave casehttps://arxiv.org/abs/2101.10695
31
5SGDLeast Squares Regression with Markovian Data: Fundamental Limits and Algorithmshttps://arxiv.org/abs/2006.08916
32
33
Robert West
34
1Keyvan Farhang RaziNLPExtending Machine Language Models toward Human-Level Language Understandinghttps://arxiv.org/abs/1912.05877
35
2Hossein TajiNLPModifying Memories in Transformer Modelshttps://arxiv.org/abs/2012.00363.pdf
36
3(Jan) Florian MaiNLPLanguage Models are Open Knowledge Graphshttps://arxiv.org/abs/2010.11967
37
4Giovanni PiccioliNLPLearning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answeringhttps://arxiv.org/abs/1911.10470
38
5Jelena SimeunovicNLPLarge Memory Layers with Product Keyshttps://papers.nips.cc/paper/2019/file/9d8df73a3cfbf3c5b47bc9b50f214aff-Paper.pdf
39
40
Boi Faltings
41
1OPtions as REsponses: Grounding Behavioural Hierarchies in Multi-Agent Reinforcement Learninghttps://arxiv.org/pdf/1906.01470.pdf
42
2Yves RychenerDecentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactionshttp://proceedings.mlr.press/v119/chang20b/chang20b.pdf
43
3Loris Di NataleLearning to Incentivize other Learning Agentshttps://arxiv.org/abs/2006.06051
44
4Hindsight and Sequential Rationality of Correlated PlayHindsight and Sequential Rationality of Correlated Play
45
5
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100